PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:1910.06017

OmniTrack: Real-time detection and tracking of objects, text and logos in video

The automatic detection and tracking of general objects (like persons, animals or cars), text and logos in a video is crucial for many video understanding tasks, and usually real-time processing as required. We propose OmniTrack, an efficient and robust algorithm which is able to automatically detect and track objects, text as well as brand logos in real-time. It combines a powerful deep learning based object detector (YoloV3) with high-quality optical flow methods. Based on the reference YoloV3 C++ implementation, we did some important performance optimizations which will be described. The major steps in the training procedure for the combined detector for text and logo will be presented. We will describe then the OmniTrack algorithm, consisting of the phases preprocessing, feature calculation, prediction, matching and update. Several performance optimizations have been implemented there as well, like doing the object detection and optical flow calculation asynchronously. Experiments show that the proposed algorithm runs in real-time for standard definition ($720x576$) video on a PC with a Quadro RTX 5000 GPU.

arXiv:2309.15782

Joint-YODNet: A Light-weight Object Detector for UAVs to Achieve Above 100fps

Small object detection via UAV (Unmanned Aerial Vehicle) images captured from drones and radar is a complex task with several formidable challenges. This domain encompasses numerous complexities that impede the accurate detection and localization of small objects. To address these challenges, we propose a novel method called JointYODNet for UAVs to detect small objects, leveraging a joint loss function specifically designed for this task. Our method revolves around the development of a joint loss function tailored to enhance the detection performance of small objects. Through extensive experimentation on a diverse dataset of UAV images captured under varying environmental conditions, we evaluated different variations of the loss function and determined the most effective formulation. The results demonstrate that our proposed joint loss function outperforms existing methods in accurately localizing small objects. Specifically, our method achieves a recall of 0.971, and a F1Score of 0.975, surpassing state-of-the-art techniques. Additionally, our method achieves a mAP@.5(%) of 98.6, indicating its robustness in detecting small objects across varying scales

arXiv:2410.15657

CL-HOI: Cross-Level Human-Object Interaction Distillation from Vision Large Language Models

Human-object interaction (HOI) detection has seen advancements with Vision Language Models (VLMs), but these methods often depend on extensive manual annotations. Vision Large Language Models (VLLMs) can inherently recognize and reason about interactions at the image level but are computationally heavy and not designed for instance-level HOI detection. To overcome these limitations, we propose a Cross-Level HOI distillation (CL-HOI) framework, which distills instance-level HOIs from VLLMs image-level understanding without the need for manual annotations. Our approach involves two stages: context distillation, where a Visual Linguistic Translator (VLT) converts visual information into linguistic form, and interaction distillation, where an Interaction Cognition Network (ICN) reasons about spatial, visual, and context relations. We design contrastive distillation losses to transfer image-level context and interaction knowledge from the teacher to the student model, enabling instance-level HOI detection. Evaluations on HICO-DET and V-COCO datasets demonstrate that our CL-HOI surpasses existing weakly supervised methods and VLLM supervised methods, showing its efficacy in detecting HOIs without manual labels.

arXiv:2411.13311공식 코드 · Papers with Code

A Resource Efficient Fusion Network for Object Detection in Bird's-Eye View using Camera and Raw Radar Data

Cameras can be used to perceive the environment around the vehicle, while affordable radar sensors are popular in autonomous driving systems as they can withstand adverse weather conditions unlike cameras. However, radar point clouds are sparser with low azimuth and elevation resolution that lack semantic and structural information of the scenes, resulting in generally lower radar detection performance. In this work, we directly use the raw range-Doppler (RD) spectrum of radar data, thus avoiding radar signal processing. We independently process camera images within the proposed comprehensive image processing pipeline. Specifically, first, we transform the camera images to Bird's-Eye View (BEV) Polar domain and extract the corresponding features with our camera encoder-decoder architecture. The resultant feature maps are fused with Range-Azimuth (RA) features, recovered from the RD spectrum input from the radar decoder to perform object detection. We evaluate our fusion strategy with other existing methods not only in terms of accuracy but also on computational complexity metrics on RADIal dataset.

arXiv:2311.01057

Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO

Smart glasses are rapidly gaining advanced functionality thanks to cutting-edge computing technologies, accelerated hardware architectures, and tiny AI algorithms. Integrating AI into smart glasses featuring a small form factor and limited battery capacity is still challenging when targeting full-day usage for a satisfactory user experience. This paper illustrates the design and implementation of tiny machine-learning algorithms exploiting novel low-power processors to enable prolonged continuous operation in smart glasses. We explore the energy- and latency-efficient of smart glasses in the case of real-time object detection. To this goal, we designed a smart glasses prototype as a research platform featuring two microcontrollers, including a novel milliwatt-power RISC-V parallel processor with a hardware accelerator for visual AI, and a Bluetooth low-power module for communication. The smart glasses integrate power cycling mechanisms, including image and audio sensing interfaces. Furthermore, we developed a family of novel tiny deep-learning models based on YOLO with sub-million parameters customized for microcontroller-based inference dubbed TinyissimoYOLO v1.3, v5, and v8, aiming at benchmarking object detection with smart glasses for energy and latency. Evaluations on the prototype of the smart glasses demonstrate TinyissimoYOLO's 17ms inference latency and 1.59mJ energy consumption per inference while ensuring acceptable detection accuracy. Further evaluation reveals an end-to-end latency from image capturing to the algorithm's prediction of 56ms or equivalently 18 fps, with a total power consumption of 62.9mW, equivalent to a 9.3 hours of continuous run time on a 154mAh battery. These results outperform MCUNet (TinyNAS+TinyEngine), which runs a simpler task (image classification) at just 7.3 fps per second.

arXiv:2408.03521공식 코드 · Papers with Code

SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection

Shadow detection is a fundamental and challenging task in many computer vision applications. Intuitively, most shadows come from the occlusion of light by the object itself, resulting in the object and its shadow being contiguous (referred to as the adjacent shadow in this paper). In this case, when the color of the object is similar to that of the shadow, existing methods struggle to achieve accurate detection. To address this problem, we present SwinShadow, a transformer-based architecture that fully utilizes the powerful shifted window mechanism for detecting adjacent shadows. The mechanism operates in two steps. Initially, it applies local self-attention within a single window, enabling the network to focus on local details. Subsequently, it shifts the attention windows to facilitate inter-window attention, enabling the capture of a broader range of adjacent information. These combined steps significantly improve the network's capacity to distinguish shadows from nearby objects. And the whole process can be divided into three parts: encoder, decoder, and feature integration. During encoding, we adopt Swin Transformer to acquire hierarchical features. Then during decoding, for shallow layers, we propose a deep supervision (DS) module to suppress the false positives and boost the representation capability of shadow features for subsequent processing, while for deep layers, we leverage a double attention (DA) module to integrate local and shifted window in one stage to achieve a larger receptive field and enhance the continuity of information. Ultimately, a new multi-level aggregation (MLA) mechanism is applied to fuse the decoded features for mask prediction. Extensive experiments on three shadow detection benchmark datasets, SBU, UCF, and ISTD, demonstrate that our network achieves good performance in terms of balance error rate (BER).

arXiv:2302.02444

Spatio-Temporal Point Process for Multiple Object Tracking

Multiple Object Tracking (MOT) focuses on modeling the relationship of detected objects among consecutive frames and merge them into different trajectories. MOT remains a challenging task as noisy and confusing detection results often hinder the final performance. Furthermore, most existing research are focusing on improving detection algorithms and association strategies. As such, we propose a novel framework that can effectively predict and mask-out the noisy and confusing detection results before associating the objects into trajectories. In particular, we formulate such "bad" detection results as a sequence of events and adopt the spatio-temporal point process}to model such events. Traditionally, the occurrence rate in a point process is characterized by an explicitly defined intensity function, which depends on the prior knowledge of some specific tasks. Thus, designing a proper model is expensive and time-consuming, with also limited ability to generalize well. To tackle this problem, we adopt the convolutional recurrent neural network (conv-RNN) to instantiate the point process, where its intensity function is automatically modeled by the training data. Furthermore, we show that our method captures both temporal and spatial evolution, which is essential in modeling events for MOT. Experimental results demonstrate notable improvements in addressing noisy and confusing detection results in MOT datasets. An improved state-of-the-art performance is achieved by incorporating our baseline MOT algorithm with the spatio-temporal point process model.

arXiv:2010.03196공식 코드 · Papers with Code

Visual Object Recognition in Indoor Environments Using Topologically Persistent Features

Object recognition in unseen indoor environments remains a challenging problem for visual perception of mobile robots. In this letter, we propose the use of topologically persistent features, which rely on the objects' shape information, to address this challenge. In particular, we extract two kinds of features, namely, sparse persistence image (PI) and amplitude, by applying persistent homology to multi-directional height function-based filtrations of the cubical complexes representing the object segmentation maps. The features are then used to train a fully connected network for recognition. For performance evaluation, in addition to a widely used shape dataset and a benchmark indoor scenes dataset, we collect a new dataset, comprising scene images from two different environments, namely, a living room and a mock warehouse. The scenes are captured using varying camera poses under different illumination conditions and include up to five different objects from a given set of fourteen objects. On the benchmark indoor scenes dataset, sparse PI features show better recognition performance in unseen environments than the features learned using the widely used ResNetV2-56 and EfficientNet-B4 models. Further, they provide slightly higher recall and accuracy values than Faster R-CNN, an end-to-end object detection method, and its state-of-the-art variant, Domain Adaptive Faster R-CNN. The performance of our methods also remains relatively unchanged from the training environment (living room) to the unseen environment (mock warehouse) in the new dataset. In contrast, the performance of the object detection methods drops substantially. We also implement the proposed method on a real-world robot to demonstrate its usefulness.

arXiv:2210.11939

Automatic Cattle Identification using YOLOv5 and Mosaic Augmentation: A Comparative Analysis

You Only Look Once (YOLO) is a single-stage object detection model popular for real-time object detection, accuracy, and speed. This paper investigates the YOLOv5 model to identify cattle in the yards. The current solution to cattle identification includes radio-frequency identification (RFID) tags. The problem occurs when the RFID tag is lost or damaged. A biometric solution identifies the cattle and helps to assign the lost or damaged tag or replace the RFID-based system. Muzzle patterns in cattle are unique biometric solutions like a fingerprint in humans. This paper aims to present our recent research in utilizing five popular object detection models, looking at the architecture of YOLOv5, investigating the performance of eight backbones with the YOLOv5 model, and the influence of mosaic augmentation in YOLOv5 by experimental results on the available cattle muzzle images. Finally, we concluded with the excellent potential of using YOLOv5 in automatic cattle identification. Our experiments show YOLOv5 with transformer performed best with mean Average Precision (mAP) 0.5 (the average of AP when the IoU is greater than 50%) of 0.995, and mAP 0.5:0.95 (the average of AP from 50% to 95% IoU with an interval of 5%) of 0.9366. In addition, our experiments show the increase in accuracy of the model by using mosaic augmentation in all backbones used in our experiments. Moreover, we can also detect cattle with partial muzzle images.

arXiv:2304.11697

Informative Data Selection with Uncertainty for Multi-modal Object Detection

Noise has always been nonnegligible trouble in object detection by creating confusion in model reasoning, thereby reducing the informativeness of the data. It can lead to inaccurate recognition due to the shift in the observed pattern, that requires a robust generalization of the models. To implement a general vision model, we need to develop deep learning models that can adaptively select valid information from multi-modal data. This is mainly based on two reasons. Multi-modal learning can break through the inherent defects of single-modal data, and adaptive information selection can reduce chaos in multi-modal data. To tackle this problem, we propose a universal uncertainty-aware multi-modal fusion model. It adopts a multi-pipeline loosely coupled architecture to combine the features and results from point clouds and images. To quantify the correlation in multi-modal information, we model the uncertainty, as the inverse of data information, in different modalities and embed it in the bounding box generation. In this way, our model reduces the randomness in fusion and generates reliable output. Moreover, we conducted a completed investigation on the KITTI 2D object detection dataset and its derived dirty data. Our fusion model is proven to resist severe noise interference like Gaussian, motion blur, and frost, with only slight degradation. The experiment results demonstrate the benefits of our adaptive fusion. Our analysis on the robustness of multi-modal fusion will provide further insights for future research.

arXiv:2312.06955

IA2U: A Transfer Plugin with Multi-Prior for In-Air Model to Underwater

In underwater environments, variations in suspended particle concentration and turbidity cause severe image degradation, posing significant challenges to image enhancement (IE) and object detection (OD) tasks. Currently, in-air image enhancement and detection methods have made notable progress, but their application in underwater conditions is limited due to the complexity and variability of these environments. Fine-tuning in-air models saves high overhead and has more optional reference work than building an underwater model from scratch. To address these issues, we design a transfer plugin with multiple priors for converting in-air models to underwater applications, named IA2U. IA2U enables efficient application in underwater scenarios, thereby improving performance in Underwater IE and OD. IA2U integrates three types of underwater priors: the water type prior that characterizes the degree of image degradation, such as color and visibility; the degradation prior, focusing on differences in details and textures; and the sample prior, considering the environmental conditions at the time of capture and the characteristics of the photographed object. Utilizing a Transformer-like structure, IA2U employs these priors as query conditions and a joint task loss function to achieve hierarchical enhancement of task-level underwater image features, therefore considering the requirements of two different tasks, IE and OD. Experimental results show that IA2U combined with an in-air model can achieve superior performance in underwater image enhancement and object detection tasks. The code will be made publicly available.

arXiv:2405.17859공식 코드 · Papers with Code

Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation

Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance. We propose a unified, simple, yet effective framework (NIDS-Net) comprising object proposal generation, embedding creation for both instance templates and proposal regions, and embedding matching for instance label assignment. Leveraging recent advancements in large vision methods, we utilize Grounding DINO and Segment Anything Model (SAM) to obtain object proposals with accurate bounding boxes and masks. Central to our approach is the generation of high-quality instance embeddings. We utilized foreground feature averages of patch embeddings from the DINOv2 ViT backbone, followed by refinement through a weight adapter mechanism that we introduce. We show experimentally that our weight adapter can adjust the embeddings locally within their feature space and effectively limit overfitting in the few-shot setting. Furthermore, the weight adapter optimizes weights to enhance the distinctiveness of instance embeddings during similarity computation. This methodology enables a straightforward matching strategy that results in significant performance gains. Our framework surpasses current state-of-the-art methods, demonstrating notable improvements in four detection datasets. In the segmentation tasks on seven core datasets of the BOP challenge, our method outperforms the leading published RGB methods and remains competitive with the best RGB-D method. We have also verified our method using real-world images from a Fetch robot and a RealSense camera. Project Page: https://irvlutd.github.io/NIDSNet/

arXiv:2412.11489공식 코드 · Papers with Code

HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection

Millimeter-wave radar plays a vital role in 3D object detection for autonomous driving due to its all-weather and all-lighting-condition capabilities for perception. However, radar point clouds suffer from pronounced sparsity and unavoidable angle estimation errors. To address these limitations, incorporating a camera may partially help mitigate the shortcomings. Nevertheless, the direct fusion of radar and camera data can lead to negative or even opposite effects due to the lack of depth information in images and low-quality image features under adverse lighting conditions. Hence, in this paper, we present the radar-camera fusion network with Hybrid Generation and Synchronization (HGSFusion), designed to better fuse radar potentials and image features for 3D object detection. Specifically, we propose the Radar Hybrid Generation Module (RHGM), which fully considers the Direction-Of-Arrival (DOA) estimation errors in radar signal processing. This module generates denser radar points through different Probability Density Functions (PDFs) with the assistance of semantic information. Meanwhile, we introduce the Dual Sync Module (DSM), comprising spatial sync and modality sync, to enhance image features with radar positional information and facilitate the fusion of distinct characteristics in different modalities. Extensive experiments demonstrate the effectiveness of our approach, outperforming the state-of-the-art methods in the VoD and TJ4DRadSet datasets by $6.53\%$ and $2.03\%$ in RoI AP and BEV AP, respectively. The code is available at https://github.com/garfield-cpp/HGSFusion.

arXiv:1705.00002

Compressive Sensing Approaches for Autonomous Object Detection in Video Sequences

Video analytics requires operating with large amounts of data. Compressive sensing allows to reduce the number of measurements required to represent the video using the prior knowledge of sparsity of the original signal, but it imposes certain conditions on the design matrix. The Bayesian compressive sensing approach relaxes the limitations of the conventional approach using the probabilistic reasoning and allows to include different prior knowledge about the signal structure. This paper presents two Bayesian compressive sensing methods for autonomous object detection in a video sequence from a static camera. Their performance is compared on the real datasets with the non-Bayesian greedy algorithm. It is shown that the Bayesian methods can provide the same accuracy as the greedy algorithm but much faster; or if the computational time is not critical they can provide more accurate results.

arXiv:1811.10002

Non-local RoI for Cross-Object Perception

We present a generic and flexible module that encodes region proposals by both their intrinsic features and the extrinsic correlations to the others. The proposed non-local region of interest (NL-RoI) can be seamlessly adapted into different generalized R-CNN architectures to better address various perception tasks. Observe that existing techniques from R-CNN treat RoIs independently and perform the prediction solely based on image features within each region proposal. However, the pairwise relationships between proposals could further provide useful information for detection and segmentation. NL-RoI is thus formulated to enrich each RoI representation with the information from all other RoIs, and yield a simple, low-cost, yet effective module for region-based convolutional networks. Our experimental results show that NL-RoI can improve the performance of Faster/Mask R-CNN for object detection and instance segmentation.

arXiv:2109.06790

A Deep Learning Approach for Masking Fetal Gender in Ultrasound Images

Ultrasound (US) imaging is highly effective with regards to both cost and versatility in real-time diagnosis; however, determination of fetal gender by US scan in the early stages of pregnancy is also a cause of sex-selective abortion. This work proposes a deep learning object detection approach to accurately mask fetal gender in US images in order to increase the accessibility of the technology. We demonstrate how the YOLOv5L architecture exhibits superior performance relative to other object detection models on this task. Our model achieves 45.8% AP[0.5:0.95], 92% F1-score and 0.006 False Positive Per Image rate on our test set. Furthermore, we introduce a bounding box delay rule based on frame-to-frame structural similarity to reduce the false negative rate by 85%, further improving masking reliability.

arXiv:2110.02670공식 코드 · Papers with Code

S-Extension Patch: A simple and efficient way to extend an object detection model

While building convolutional network-based systems, the toll it takes to train the network is something that cannot be ignored. In cases where we need to append additional capabilities to the existing model, the attention immediately goes towards retraining techniques. In this paper, I show how to leverage knowledge about the dataset to append the class faster while maintaining the speed of inference as well as the accuracies; while reducing the amount of time and data required. The method can extend a class in the existing object detection model in 1/10th of the time compared to the other existing methods. S-Extension patch not only offers faster training but also speed and ease of adaptation, as it can be appended to any existing system, given it fulfills the similarity threshold condition.

arXiv:2210.08715

ReAFFPN: Rotation-equivariant Attention Feature Fusion Pyramid Networks for Aerial Object Detection

This paper proposes a Rotation-equivariant Attention Feature Fusion Pyramid Networks for Aerial Object Detection named ReAFFPN. ReAFFPN aims at improving the effect of rotation-equivariant features fusion between adjacent layers which suffers from the semantic and scale discontinuity. Due to the particularity of rotational equivariant convolution, general methods are unable to achieve their original effect while ensuring rotation equivariance of the network. To solve this problem, we design a new Rotation-equivariant Channel Attention which has the ability to both generate channel attention and keep rotation equivariance. Then we embed a new channel attention function into Iterative Attentional Feature Fusion (iAFF) module to realize Rotation-equivariant Attention Feature Fusion. Experimental results demonstrate that ReAFFPN achieves a better rotation-equivariant feature fusion ability and significantly improve the accuracy of the Rotation-equivariant Convolutional Networks.

arXiv:2406.03229

Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models

As transformer-based object detection models progress, their impact in critical sectors like autonomous vehicles and aviation is expected to grow. Soft errors causing bit flips during inference have significantly impacted DNN performance, altering predictions. Traditional range restriction solutions for CNNs fall short for transformers. This study introduces the Global Clipper and Global Hybrid Clipper, effective mitigation strategies specifically designed for transformer-based models. It significantly enhances their resilience to soft errors and reduces faulty inferences to ~ 0\%. We also detail extensive testing across over 64 scenarios involving two transformer models (DINO-DETR and Lite-DETR) and two CNN models (YOLOv3 and SSD) using three datasets, totalling approximately 3.3 million inferences, to assess model robustness comprehensively. Moreover, the paper explores unique aspects of attention blocks in transformers and their operational differences from CNNs.

arXiv:2504.10877

Weather-Aware Object Detection Transformer for Domain Adaptation

RT-DETRs have shown strong performance across various computer vision tasks but are known to degrade under challenging weather conditions such as fog. In this work, we investigate three novel approaches to enhance RT-DETR robustness in foggy environments: (1) Domain Adaptation via Perceptual Loss, which distills domain-invariant features from a teacher network to a student using perceptual supervision; (2) Weather Adaptive Attention, which augments the attention mechanism with fog-sensitive scaling by introducing an auxiliary foggy image stream; and (3) Weather Fusion Encoder, which integrates a dual-stream encoder architecture that fuses clear and foggy image features via multi-head self and cross-attention. Despite the architectural innovations, none of the proposed methods consistently outperform the baseline RT-DETR. We analyze the limitations and potential causes, offering insights for future research in weather-aware object detection.