PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2004.08595

Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton

In this paper, we solve three low-level pixel-wise vision problems, including salient object segmentation, edge detection, and skeleton extraction, within a unified framework. We first show some similarities shared by these tasks and then demonstrate how they can be leveraged for developing a unified framework that can be trained end-to-end. In particular, we introduce a selective integration module that allows each task to dynamically choose features at different levels from the shared backbone based on its own characteristics. Furthermore, we design a task-adaptive attention module, aiming at intelligently allocating information for different tasks according to the image content priors. To evaluate the performance of our proposed network on these tasks, we conduct exhaustive experiments on multiple representative datasets. We will show that though these tasks are naturally quite different, our network can work well on all of them and even perform better than current single-purpose state-of-the-art methods. In addition, we also conduct adequate ablation analyses that provide a full understanding of the design principles of the proposed framework. To facilitate future research, source code will be released.

arXiv:2012.00257공식 코드 · Papers with Code

Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection

Confluence is a novel non-Intersection over Union (IoU) alternative to Non-Maxima Suppression (NMS) in bounding box post-processing in object detection. It overcomes the inherent limitations of IoU-based NMS variants to provide a more stable, consistent predictor of bounding box clustering by using a normalized Manhattan Distance inspired proximity metric to represent bounding box clustering. Unlike Greedy and Soft NMS, it does not rely solely on classification confidence scores to select optimal bounding boxes, instead selecting the box which is closest to every other box within a given cluster and removing highly confluent neighboring boxes. Confluence is experimentally validated on the MS COCO and CrowdHuman benchmarks, improving Average Precision by up to 2.3-3.8% and Average Recall by up to 5.3-7.2% when compared against de-facto standard and state of the art NMS variants. Quantitative results are supported by extensive qualitative analysis and threshold sensitivity analysis experiments support the conclusion that Confluence is more robust than NMS variants. Confluence represents a paradigm shift in bounding box processing, with potential to replace IoU in bounding box regression processes.

arXiv:2407.17664

SDLNet: Statistical Deep Learning Network for Co-Occurring Object Detection and Identification

With the growing advances in deep learning based technologies the detection and identification of co-occurring objects is a challenging task which has many applications in areas such as, security and surveillance. In this paper, we propose a novel framework called SDLNet- Statistical analysis with Deep Learning Network that identifies co-occurring objects in conjunction with base objects in multilabel object categories. The pipeline of proposed work is implemented in two stages: in the first stage of SDLNet we deal with multilabel detectors for discovering labels, and in the second stage we perform co-occurrence matrix analysis. In co-occurrence matrix analysis, we learn co-occurrence statistics by setting base classes and frequently occurring classes, following this we build association rules and generate frequent patterns. The crucial part of SDLNet is recognizing base classes and making consideration for co-occurring classes. Finally, the generated co-occurrence matrix based on frequent patterns will show base classes and their corresponding co-occurring classes. SDLNet is evaluated on two publicly available datasets: Pascal VOC and MS-COCO. The experimental results on these benchmark datasets are reported in Sec 4.

arXiv:2108.06152공식 코드 · Papers with Code

Conditional DETR for Fast Training Convergence

The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a conditional cross-attention mechanism for fast DETR training. Our approach is motivated by that the cross-attention in DETR relies highly on the content embeddings for localizing the four extremities and predicting the box, which increases the need for high-quality content embeddings and thus the training difficulty. Our approach, named conditional DETR, learns a conditional spatial query from the decoder embedding for decoder multi-head cross-attention. The benefit is that through the conditional spatial query, each cross-attention head is able to attend to a band containing a distinct region, e.g., one object extremity or a region inside the object box. This narrows down the spatial range for localizing the distinct regions for object classification and box regression, thus relaxing the dependence on the content embeddings and easing the training. Empirical results show that conditional DETR converges 6.7x faster for the backbones R50 and R101 and 10x faster for stronger backbones DC5-R50 and DC5-R101. Code is available at https://github.com/Atten4Vis/ConditionalDETR.

arXiv:2411.08433

3D Multi-Object Tracking with Semi-Supervised GRU-Kalman Filter

3D Multi-Object Tracking (MOT), a fundamental component of environmental perception, is essential for intelligent systems like autonomous driving and robotic sensing. Although Tracking-by-Detection frameworks have demonstrated excellent performance in recent years, their application in real-world scenarios faces significant challenges. Object movement in complex environments is often highly nonlinear, while existing methods typically rely on linear approximations of motion. Furthermore, system noise is frequently modeled as a Gaussian distribution, which fails to capture the true complexity of the noise dynamics. These oversimplified modeling assumptions can lead to significant reductions in tracking precision. To address this, we propose a GRU-based MOT method, which introduces a learnable Kalman filter into the motion module. This approach is able to learn object motion characteristics through data-driven learning, thereby avoiding the need for manual model design and model error. At the same time, to avoid abnormal supervision caused by the wrong association between annotations and trajectories, we design a semi-supervised learning strategy to accelerate the convergence speed and improve the robustness of the model. Evaluation experiment on the nuScenes and Argoverse2 datasets demonstrates that our system exhibits superior performance and significant potential compared to traditional TBD methods.

arXiv:2503.14012공식 코드 · Papers with Code

LEGNet: Lightweight Edge-Gaussian Driven Network for Low-Quality Remote Sensing Image Object Detection

Remote sensing object detection (RSOD) faces formidable challenges in complex visual environments. Aerial and satellite images inherently suffer from limitations such as low spatial resolution, sensor noise, blurred objects, low-light degradation, and partial occlusions. These degradation factors collectively compromise the feature discriminability in detection models, resulting in three key issues: (1) reduced contrast that hampers foreground-background separation, (2) structural discontinuities in edge representations, and (3) ambiguous feature responses caused by variations in illumination. These collectively weaken model robustness and deployment feasibility. To address these challenges, we propose LEGNet, a lightweight network that incorporates a novel edge-Gaussian aggregation (EGA) module specifically designed for low-quality remote sensing images. Our key innovation lies in the synergistic integration of Scharr operator-based edge priors with uncertainty-aware Gaussian modeling: (a) The orientation-aware Scharr filters preserve high-frequency edge details with rotational invariance; (b) The uncertainty-aware Gaussian layers probabilistically refine low-confidence features through variance estimation. This design enables precision enhancement while maintaining architectural simplicity. Comprehensive evaluations across four RSOD benchmarks (DOTA-v1.0, v1.5, DIOR-R, FAIR1M-v1.0) and a UAV-view dataset (VisDrone2019) demonstrate significant improvements. LEGNet achieves state-of-the-art performance across five benchmark datasets while ensuring computational efficiency, making it well-suited for deployment on resource-constrained edge devices in real-world remote sensing applications. The code is available at https://github.com/lwCVer/LEGNet.

arXiv:2609.22706v1cs.CV

DOA-SORT: 분포적 관측을 활용한 방향성 가림 인지 다중 객체 추적

DOA-SORT: Directional Occlusion-Aware Multi-Object Tracking with Distributional Observations

다중 객체 추적(MOT)에서 객체 식별 연관(identity association)은 부분적 가림(partial occlusion), 잘린 탐지(truncated detection), 변동하는 신뢰도 점수에 취약합니다. 기존의 모션 위주 트래커들은 흔히 가림을 스칼라 페널티로 표현합니다. 이러한 방식은 가림으로 인해 발생하는 방향성 관측 바이어스(bias)를 놓치게 됩니다. 즉, 좌, 우, 상, 하 가림은 탐지된 객체의 위치와 형태를 서로 다른 방식으로 왜곡합니다. 본 논문에서는 이러한 바이어스를 명시적으로 모델링하는 온라인 기반의 무학습(training-free) 트래커인 DOA-SORT(Directional Occlusion-Aware SORT)를 제안합니다. 먼저, 바운딩 박스 중첩과 상대적인 하단 위치로부터 소프트한 앞뒤 순서를 추론하고 방향별 가림 범위 및 깊이를 추정합니다. 그런 다음 깨끗한 관측 요소 하나와 네 가지 방향성 가림 관측 요소의 혼합을 구성합니다. 해당 모델은 박스 중심, 면적, 신뢰도, 종횡비로 구성된 5차원 관측을 사용하며, 예측된 가림과 탐지 신뢰도에 맞춰 관측 노이즈를 적응시킵니다. 이 방향성 혼합 가능도(likelihood)는 높은 신뢰도 연관, 낮은 신뢰도 연관, 트랙 복구에 사용되며, 모호성 페널티와 국소 순서 일관성 교환(local order-consistency swap)을 통해 인접한 객체 간의 식별 오류를 더욱 줄입니다. DanceTrack 검증(validation) 분할에서 DOA-SORT는 동일한 탐지기 및 평가 프로토콜을 사용한 OA-SORT 대비 HOTA를 63.00에서 66.34로, AssA를 45.10에서 49.57로, IDF1을 62.19에서 65.28로 향상시켰습니다. 탐지 정확도는 안정적으로 유지되는 반면 성능 향상은 연관 품질에 집중되었습니다. MOT17 및 MOT20 학습(train) 분할에 대한 추가적인 국소 평가는 동일한 no-ReID 추적 프로토콜 하에서 데이터셋 간 동작 특성을 보여줍니다.

arXiv:2103.14878공식 코드 · Papers with Code

COVID-19 personal protective equipment detection using real-time deep learning methods

The exponential spread of COVID-19 in over 215 countries has led WHO to recommend face masks and gloves for a safe return to school or work. We used artificial intelligence and deep learning algorithms for automatic face masks and gloves detection in public areas. We investigated and assessed the efficacy of two popular deep learning algorithms of YOLO (You Only Look Once) and SSD MobileNet for the detection and proper wearing of face masks and gloves trained over a data set of 8250 images imported from the internet. YOLOv3 is implemented using the DarkNet framework, and the SSD MobileNet algorithm is applied for the development of accurate object detection. The proposed models have been developed to provide accurate multi-class detection (Mask vs. No-Mask vs. Gloves vs. No-Gloves vs. Improper). When people wear their masks improperly, the method detects them as an improper class. The introduced models provide accuracies of (90.6% for YOLO and 85.5% for SSD) for multi-class detection. The systems' results indicate the efficiency and validity of detecting people who do not wear masks and gloves in public.

arXiv:2201.05290

Argus++: Robust Real-time Activity Detection for Unconstrained Video Streams with Overlapping Cube Proposals

Activity detection is one of the attractive computer vision tasks to exploit the video streams captured by widely installed cameras. Although achieving impressive performance, conventional activity detection algorithms are usually designed under certain constraints, such as using trimmed and/or object-centered video clips as inputs. Therefore, they failed to deal with the multi-scale multi-instance cases in real-world unconstrained video streams, which are untrimmed and have large field-of-views. Real-time requirements for streaming analysis also mark brute force expansion of them unfeasible. To overcome these issues, we propose Argus++, a robust real-time activity detection system for analyzing unconstrained video streams. The design of Argus++ introduces overlapping spatio-temporal cubes as an intermediate concept of activity proposals to ensure coverage and completeness of activity detection through over-sampling. The overall system is optimized for real-time processing on standalone consumer-level hardware. Extensive experiments on different surveillance and driving scenarios demonstrated its superior performance in a series of activity detection benchmarks, including CVPR ActivityNet ActEV 2021, NIST ActEV SDL UF/KF, TRECVID ActEV 2020/2021, and ICCV ROAD 2021.

arXiv:2410.05096

Human-in-the-loop Reasoning For Traffic Sign Detection: Collaborative Approach Yolo With Video-llava

Traffic Sign Recognition (TSR) detection is a crucial component of autonomous vehicles. While You Only Look Once (YOLO) is a popular real-time object detection algorithm, factors like training data quality and adverse weather conditions (e.g., heavy rain) can lead to detection failures. These failures can be particularly dangerous when visual similarities between objects exist, such as mistaking a 30 km/h sign for a higher speed limit sign. This paper proposes a method that combines video analysis and reasoning, prompting with a human-in-the-loop guide large vision model to improve YOLOs accuracy in detecting road speed limit signs, especially in semi-real-world conditions. It is hypothesized that the guided prompting and reasoning abilities of Video-LLava can enhance YOLOs traffic sign detection capabilities. This hypothesis is supported by an evaluation based on human-annotated accuracy metrics within a dataset of recorded videos from the CARLA car simulator. The results demonstrate that a collaborative approach combining YOLO with Video-LLava and reasoning can effectively address challenging situations such as heavy rain and overcast conditions that hinder YOLOs detection capabilities.

논문 ID: document/9301932

Automatic Detection and Image Recognition of Precision Agriculture for Citrus Diseases

In recent years, the development of precision agriculture is a new technology. The main reason for the automation of agricultural processes is to save the time and energy required to perform repeated farming tasks and to increase production by treating each crop separately and applying smart agricultural concepts. In this paper, an automatic detection and image recognition of citrus diseases is presented that can help farmer find the disease and identify it from the captured images. This method use YOLO(You Only Look Once) algorithm which is an object detection model to detect and recognize the diseases from citrus leaf images. YOLO can realtime detect the disease and circle around it on the image and video. The dataset includes images of citrus leaf with two kinds of diseases: Citrus Canker, Citrus Greening.

arXiv:2611.07553v1cs.CV

레이아웃-지시 조건 확산 합성을 통한 롱테일 검출 개선

Improving Long-Tail Detection via Layout-Instruction Conditioned Diffusion Synthesis

확산 모델이 생성한 합성 데이터는 객체 검출을 향상시킬 수 있으나, 희소한 드문 클래스와 유연하지 못한 조건 설정(예: 텍스트 전용 또는 레이아웃 전용 입력) 때문에 롱테일 성능은 여전히 제한적이다. 본 논문에서는 텍스트, 레이아웃 또는 이 둘의 혼합을 지원하는 레이아웃-지시 조건 스테이블 디퓨전 프레임워크인 Tail-SD를 제안한다. 이를 통해 박스, 마스크 및/또는 프롬프트로부터 제어 가능한 합성을 수행하여 롱테일 객체를 더 잘 포괄할 수 있다. 이질적인 조건들에 걸쳐 단일 모델을 학습하기 위해 멀티태스크 교차 어텐션 모듈과 멀티태스크 임베딩 토큰을 도입하여 생성 품질과 다양성을 향상시킨다. COCO와 LVIS에 대한 광범위한 실험을 통해 혼합 조건을 사용한 확산 합성이 일관되게 검출에 도움이 됨을 보이며, 예를 들어 LVIS val에서 희귀 클래스 Box/Mask AP가 +4.89% / +5.68% 향상되어 롱테일 문제 해결에 대한 큰 잠재력을 보여 준다.

arXiv:1905.07754공식 코드 · Papers with Code

Multimodal 3D Object Detection from Simulated Pretraining

The need for simulated data in autonomous driving applications has become increasingly important, both for validation of pretrained models and for training new models. In order for these models to generalize to real-world applications, it is critical that the underlying dataset contains a variety of driving scenarios and that simulated sensor readings closely mimics real-world sensors. We present the Carla Automated Dataset Extraction Tool (CADET), a novel tool for generating training data from the CARLA simulator to be used in autonomous driving research. The tool is able to export high-quality, synchronized LIDAR and camera data with object annotations, and offers configuration to accurately reflect a real-life sensor array. Furthermore, we use this tool to generate a dataset consisting of 10 000 samples and use this dataset in order to train the 3D object detection network AVOD-FPN, with finetuning on the KITTI dataset in order to evaluate the potential for effective pretraining. We also present two novel LIDAR feature map configurations in Bird's Eye View for use with AVOD-FPN that can be easily modified. These configurations are tested on the KITTI and CADET datasets in order to evaluate their performance as well as the usability of the simulated dataset for pretraining. Although insufficient to fully replace the use of real world data, and generally not able to exceed the performance of systems fully trained on real data, our results indicate that simulated data can considerably reduce the amount of training on real data required to achieve satisfactory levels of accuracy.

arXiv:2011.10278공식 코드 · Papers with Code

Joint Representation of Temporal Image Sequences and Object Motion for Video Object Detection

In this paper, we propose a new video object detector (VoD) method referred to as temporal feature aggregation and motion-aware VoD (TM-VoD), which produces a joint representation of temporal image sequences and object motion. The proposed TM-VoD aggregates visual feature maps extracted by convolutional neural networks applying the temporal attention gating and spatial feature alignment. This temporal feature aggregation is performed in two stages in a hierarchical fashion. In the first stage, the visual feature maps are fused at a pixel level via gated attention model. In the second stage, the proposed method aggregates the features after aligning the object features using temporal box offset calibration and weights them according to the cosine similarity measure. The proposed TM-VoD also finds the representation of the motion of objects in two successive steps. The pixel-level motion features are first computed based on the incremental changes between the adjacent visual feature maps. Then, box-level motion features are obtained from both the region of interest (RoI)-aligned pixel-level motion features and the sequential changes of the box coordinates. Finally, all these features are concatenated to produce a joint representation of the objects for VoD. The experiments conducted on the ImageNet VID dataset demonstrate that the proposed method outperforms existing VoD methods and achieves a performance comparable to that of state-of-the-art VoDs.

arXiv:1904.06493공식 코드 · Papers with Code

Rethinking Classification and Localization for Object Detection

Two head structures (i.e. fully connected head and convolution head) have been widely used in R-CNN based detectors for classification and localization tasks. However, there is a lack of understanding of how does these two head structures work for these two tasks. To address this issue, we perform a thorough analysis and find an interesting fact that the two head structures have opposite preferences towards the two tasks. Specifically, the fully connected head (fc-head) is more suitable for the classification task, while the convolution head (conv-head) is more suitable for the localization task. Furthermore, we examine the output feature maps of both heads and find that fc-head has more spatial sensitivity than conv-head. Thus, fc-head has more capability to distinguish a complete object from part of an object, but is not robust to regress the whole object. Based upon these findings, we propose a Double-Head method, which has a fully connected head focusing on classification and a convolution head for bounding box regression. Without bells and whistles, our method gains +3.5 and +2.8 AP on MS COCO dataset from Feature Pyramid Network (FPN) baselines with ResNet-50 and ResNet-101 backbones, respectively.

arXiv:1605.02196

All Weather Perception: Joint Data Association, Tracking, and Classification for Autonomous Ground Vehicles

A novel probabilistic perception algorithm is presented as a real-time joint solution to data association, object tracking, and object classification for an autonomous ground vehicle in all-weather conditions. The presented algorithm extends a Rao-Blackwellized Particle Filter originally built with a particle filter for data association and a Kalman filter for multi-object tracking (Miller et al. 2011a) to now also include multiple model tracking for classification. Additionally a state-of-the-art vision detection algorithm that includes heading information for autonomous ground vehicle (AGV) applications was implemented. Cornell's AGV from the DARPA Urban Challenge was upgraded and used to experimentally examine if and how state-of-the-art vision algorithms can complement or replace lidar and radar sensors. Sensor and algorithm performance in adverse weather and lighting conditions is tested. Experimental evaluation demonstrates robust all-weather data association, tracking, and classification where camera, lidar, and radar sensors complement each other inside the joint probabilistic perception algorithm.

arXiv:2102.04582

RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection

Over the last few decades, many architectures have been developed that harness the power of neural networks to detect objects in near real-time. Training such systems requires substantial time across multiple GPUs and massive labeled training datasets. Although the goal of these systems is generalizability, they are often impractical in real-life applications due to flexibility, robustness, or speed issues. This paper proposes RMOPP: A robust multi-objective post-processing algorithm to boost the performance of fast pre-trained object detectors with a negligible impact on their speed. Specifically, RMOPP is a statistically driven, post-processing algorithm that allows for simultaneous optimization of precision and recall. A unique feature of RMOPP is the Pareto frontier that identifies dominant possible post-processed detectors to optimize for both precision and recall. RMOPP explores the full potential of a pre-trained object detector and is deployable for near real-time predictions. We also provide a compelling test case on YOLOv2 using the MS-COCO dataset.

arXiv:1806.06946

Semantic Image Retrieval by Uniting Deep Neural Networks and Cognitive Architectures

Image and video retrieval by their semantic content has been an important and challenging task for years, because it ultimately requires bridging the symbolic/subsymbolic gap. Recent successes in deep learning enabled detection of objects belonging to many classes greatly outperforming traditional computer vision techniques. However, deep learning solutions capable of executing retrieval queries are still not available. We propose a hybrid solution consisting of a deep neural network for object detection and a cognitive architecture for query execution. Specifically, we use YOLOv2 and OpenCog. Queries allowing the retrieval of video frames containing objects of specified classes and specified spatial arrangement are implemented.

arXiv:2408.05974공식 코드 · Papers with Code

Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection

Zero-shot human-object interaction (HOI) detector is capable of generalizing to HOI categories even not encountered during training. Inspired by the impressive zero-shot capabilities offered by CLIP, latest methods strive to leverage CLIP embeddings for improving zero-shot HOI detection. However, these embedding-based methods train the classifier on seen classes only, inevitably resulting in seen-unseen confusion for the model during inference. Besides, we find that using prompt-tuning and adapters further increases the gap between seen and unseen accuracy. To tackle this challenge, we present the first generation-based model using CLIP for zero-shot HOI detection, coined HOIGen. It allows to unlock the potential of CLIP for feature generation instead of feature extraction only. To achieve it, we develop a CLIP-injected feature generator in accordance with the generation of human, object and union features. Then, we extract realistic features of seen samples and mix them with synthetic features together, allowing the model to train seen and unseen classes jointly. To enrich the HOI scores, we construct a generative prototype bank in a pairwise HOI recognition branch, and a multi-knowledge prototype bank in an image-wise HOI recognition branch, respectively. Extensive experiments on HICO-DET benchmark demonstrate our HOIGen achieves superior performance for both seen and unseen classes under various zero-shot settings, compared with other top-performing methods. Code is available at: https://github.com/soberguo/HOIGen

arXiv:2501.18835

Early Diagnosis and Severity Assessment of Weligama Coconut Leaf Wilt Disease and Coconut Caterpillar Infestation using Deep Learning-based Image Processing Techniques

Global Coconut (Cocos nucifera (L.)) cultivation faces significant challenges, including yield loss, due to pest and disease outbreaks. In particular, Weligama Coconut Leaf Wilt Disease (WCWLD) and Coconut Caterpillar Infestation (CCI) damage coconut trees, causing severe coconut production loss in Sri Lanka and nearby coconut-producing countries. Currently, both WCWLD and CCI are detected through on-field human observations, a process that is not only time-consuming but also limits the early detection of infections. This paper presents a study conducted in Sri Lanka, demonstrating the effectiveness of employing transfer learning-based Convolutional Neural Network (CNN) and Mask Region-based-CNN (Mask R-CNN) to identify WCWLD and CCI at their early stages and to assess disease progression. Further, this paper presents the use of the You Only Look Once (YOLO) object detection model to count the number of caterpillars distributed on leaves with CCI. The introduced methods were tested and validated using datasets collected from Matara, Puttalam, and Makandura, Sri Lanka. The results show that the proposed methods identify WCWLD and CCI with an accuracy of 90% and 95%, respectively. In addition, the proposed WCWLD disease severity identification method classifies the severity with an accuracy of 97%. Furthermore, the accuracies of the object detection models for calculating the number of caterpillars in the leaflets were: YOLOv5-96.87%, YOLOv8-96.1%, and YOLO11-95.9%.