PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2303.13753

EMS-Net: Efficient Multi-Temporal Self-Attention For Hyperspectral Change Detection

Hyperspectral change detection plays an essential role of monitoring the dynamic urban development and detecting precise fine object evolution and alteration. In this paper, we have proposed an original Efficient Multi-temporal Self-attention Network (EMS-Net) for hyperspectral change detection. The designed EMS module cuts redundancy of those similar and containing-no-changes feature maps, computing efficient multi-temporal change information for precise binary change map. Besides, to explore the clustering characteristics of the change detection, a novel supervised contrastive loss is provided to enhance the compactness of the unchanged. Experiments implemented on two hyperspectral change detection datasets manifests the out-standing performance and validity of proposed method.

arXiv:1705.07328

Forecasting Hands and Objects in Future Frames

This paper presents an approach to forecast future presence and location of human hands and objects. Given an image frame, the goal is to predict what objects will appear in the future frame (e.g., 5 seconds later) and where they will be located at, even when they are not visible in the current frame. The key idea is that (1) an intermediate representation of a convolutional object recognition model abstracts scene information in its frame and that (2) we can predict (i.e., regress) such representations corresponding to the future frames based on that of the current frame. We design a new two-stream convolutional neural network (CNN) architecture for videos by extending the state-of-the-art convolutional object detection network, and present a new fully convolutional regression network for predicting future scene representations. Our experiments confirm that combining the regressed future representation with our detection network allows reliable estimation of future hands and objects in videos. We obtain much higher accuracy compared to the state-of-the-art future object presence forecast method on a public dataset.

arXiv:1611.06069

DeepVO: A Deep Learning approach for Monocular Visual Odometry

Deep Learning based techniques have been adopted with precision to solve a lot of standard computer vision problems, some of which are image classification, object detection and segmentation. Despite the widespread success of these approaches, they have not yet been exploited largely for solving the standard perception related problems encountered in autonomous navigation such as Visual Odometry (VO), Structure from Motion (SfM) and Simultaneous Localization and Mapping (SLAM). This paper analyzes the problem of Monocular Visual Odometry using a Deep Learning-based framework, instead of the regular 'feature detection and tracking' pipeline approaches. Several experiments were performed to understand the influence of a known/unknown environment, a conventional trackable feature and pre-trained activations tuned for object classification on the network's ability to accurately estimate the motion trajectory of the camera (or the vehicle). Based on these observations, we propose a Convolutional Neural Network architecture, best suited for estimating the object's pose under known environment conditions, and displays promising results when it comes to inferring the actual scale using just a single camera in real-time.

arXiv:2103.11279

Scalable Detection and Tracking of Geometric Extended Objects

Multiobject tracking provides situational awareness that enables new applications for modern convenience, public safety, and homeland security. This paper presents a factor graph formulation and a particle-based sum-product algorithm (SPA) for scalable detection and tracking of extended objects. The proposed method dynamically introduces states of newly detected objects, efficiently performs probabilistic multiple-measurement to object association, and jointly infers the geometric shapes of objects. Scalable extended object tracking (EOT) is enabled by modeling association uncertainty by measurement-oriented association variables and newly detected objects by a Poisson birth process. Contrary to conventional EOT methods, a fully particle-based approach makes it possible to describe different geometric object shapes. The proposed method can reliably detect, localize, and track a large number of closely-spaced extended objects without gating and clustering of measurements. We demonstrate significant performance advantages of our approach compared to the recently introduced Poisson multi-Bernoulli mixture filter. In particular, we consider a simulated scenarios with up to twenty closely-spaced objects and a real autonomous driving application where measurements are captured by a lidar sensor.

arXiv:2108.11101

Detecting Small Objects in Thermal Images Using Single-Shot Detector

SSD (Single Shot Multibox Detector) is one of the most successful object detectors for its high accuracy and fast speed. However, the features from shallow layer (mainly Conv4_3) of SSD lack semantic information, resulting in poor performance in small objects. In this paper, we proposed DDSSD (Dilation and Deconvolution Single Shot Multibox Detector), an enhanced SSD with a novel feature fusion module which can improve the performance over SSD for small object detection. In the feature fusion module, dilation convolution module is utilized to enlarge the receptive field of features from shallow layer and deconvolution module is adopted to increase the size of feature maps from high layer. Our network achieves 79.7% mAP on PASCAL VOC2007 test and 28.3% mmAP on MS COCO test-dev at 41 FPS with only 300x300 input using a single Nvidia 1080 GPU. Especially, for small objects, DDSSD achieves 10.5% on MS COCO and 22.8% on FLIR thermal dataset, outperforming a lot of state-of-the-art object detection algorithms in both aspects of accuracy and speed.

arXiv:2303.10937

Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depth

Despite recent attention and exploration of depth for various tasks, it is still an unexplored modality for weakly-supervised object detection (WSOD). We propose an amplifier method for enhancing the performance of WSOD by integrating depth information. Our approach can be applied to any WSOD method based on multiple-instance learning, without necessitating additional annotations or inducing large computational expenses. Our proposed method employs a monocular depth estimation technique to obtain hallucinated depth information, which is then incorporated into a Siamese WSOD network using contrastive loss and fusion. By analyzing the relationship between language context and depth, we calculate depth priors to identify the bounding box proposals that may contain an object of interest. These depth priors are then utilized to update the list of pseudo ground-truth boxes, or adjust the confidence of per-box predictions. Our proposed method is evaluated on six datasets (COCO, PASCAL VOC, Conceptual Captions, Clipart1k, Watercolor2k, and Comic2k) by implementing it on top of two state-of-the-art WSOD methods, and we demonstrate a substantial enhancement in performance.

arXiv:2305.02034공식 코드 · Papers with Code

SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model

The success of the Segment Anything Model (SAM) demonstrates the significance of data-centric machine learning. However, due to the difficulties and high costs associated with annotating Remote Sensing (RS) images, a large amount of valuable RS data remains unlabeled, particularly at the pixel level. In this study, we leverage SAM and existing RS object detection datasets to develop an efficient pipeline for generating a large-scale RS segmentation dataset, dubbed SAMRS. SAMRS totally possesses 105,090 images and 1,668,241 instances, surpassing existing high-resolution RS segmentation datasets in size by several orders of magnitude. It provides object category, location, and instance information that can be used for semantic segmentation, instance segmentation, and object detection, either individually or in combination. We also provide a comprehensive analysis of SAMRS from various aspects. Moreover, preliminary experiments highlight the importance of conducting segmentation pre-training with SAMRS to address task discrepancies and alleviate the limitations posed by limited training data during fine-tuning. The code and dataset will be available at https://github.com/ViTAE-Transformer/SAMRS.

arXiv:2506.13505

UAV Object Detection and Positioning in a Mining Industrial Metaverse with Custom Geo-Referenced Data

The mining sector increasingly adopts digital tools to improve operational efficiency, safety, and data-driven decision-making. One of the key challenges remains the reliable acquisition of high-resolution, geo-referenced spatial information to support core activities such as extraction planning and on-site monitoring. This work presents an integrated system architecture that combines UAV-based sensing, LiDAR terrain modeling, and deep learning-based object detection to generate spatially accurate information for open-pit mining environments. The proposed pipeline includes geo-referencing, 3D reconstruction, and object localization, enabling structured spatial outputs to be integrated into an industrial digital twin platform. Unlike traditional static surveying methods, the system offers higher coverage and automation potential, with modular components suitable for deployment in real-world industrial contexts. While the current implementation operates in post-flight batch mode, it lays the foundation for real-time extensions. The system contributes to the development of AI-enhanced remote sensing in mining by demonstrating a scalable and field-validated geospatial data workflow that supports situational awareness and infrastructure safety.

arXiv:1909.02225

POD: Practical Object Detection with Scale-Sensitive Network

Scale-sensitive object detection remains a challenging task, where most of the existing methods could not learn it explicitly and are not robust to scale variance. In addition, the most existing methods are less efficient during training or slow during inference, which are not friendly to real-time applications. In this paper, we propose a practical object detection method with scale-sensitive network.Our method first predicts a global continuous scale ,which is shared by all position, for each convolution filter of each network stage. To effectively learn the scale, we average the spatial features and distill the scale from channels. For fast-deployment, we propose a scale decomposition method that transfers the robust fractional scale into combination of fixed integral scales for each convolution filter, which exploits the dilated convolution. We demonstrate it on one-stage and two-stage algorithms under different configurations. For practical applications, training of our method is of efficiency and simplicity which gets rid of complex data sampling or optimize strategy. During test-ing, the proposed method requires no extra operation and is very supportive of hardware acceleration like TensorRT and TVM. On the COCO test-dev, our model could achieve a 41.5 mAP on one-stage detector and 42.1 mAP on two-stage detectors based on ResNet-101, outperforming base-lines by 2.4 and 2.1 respectively without extra FLOPS.

arXiv:2105.13279

Dynamic Network selection for the Object Detection task: why it matters and what we (didn't) achieve

In this paper, we want to show the potential benefit of a dynamic auto-tuning approach for the inference process in the Deep Neural Network (DNN) context, tackling the object detection challenge. We benchmarked different neural networks to find the optimal detector for the well-known COCO 17 database, and we demonstrate that even if we only consider the quality of the prediction there is not a single optimal network. This is even more evident if we also consider the time to solution as a metric to evaluate, and then select, the most suitable network. This opens to the possibility for an adaptive methodology to switch among different object detection networks according to run-time requirements (e.g. maximum quality subject to a time-to-solution constraint). Moreover, we demonstrated by developing an ad hoc oracle, that an additional proactive methodology could provide even greater benefits, allowing us to select the best network among the available ones given some characteristics of the processed image. To exploit this method, we need to identify some image features that can be used to steer the decision on the most promising network. Despite the optimization opportunity that has been identified, we were not able to identify a predictor function that validates this attempt neither adopting classical image features nor by using a DNN classifier.

arXiv:2112.11790공식 코드 · Papers with Code

BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View

Autonomous driving perceives its surroundings for decision making, which is one of the most complex scenarios in visual perception. The success of paradigm innovation in solving the 2D object detection task inspires us to seek an elegant, feasible, and scalable paradigm for fundamentally pushing the performance boundary in this area. To this end, we contribute the BEVDet paradigm in this paper. BEVDet performs 3D object detection in Bird-Eye-View (BEV), where most target values are defined and route planning can be handily performed. We merely reuse existing modules to build its framework but substantially develop its performance by constructing an exclusive data augmentation strategy and upgrading the Non-Maximum Suppression strategy. In the experiment, BEVDet offers an excellent trade-off between accuracy and time-efficiency. As a fast version, BEVDet-Tiny scores 31.2% mAP and 39.2% NDS on the nuScenes val set. It is comparable with FCOS3D, but requires just 11% computational budget of 215.3 GFLOPs and runs 9.2 times faster at 15.6 FPS. Another high-precision version dubbed BEVDet-Base scores 39.3% mAP and 47.2% NDS, significantly exceeding all published results. With a comparable inference speed, it surpasses FCOS3D by a large margin of +9.8% mAP and +10.0% NDS. The source code is publicly available for further research at https://github.com/HuangJunJie2017/BEVDet .

arXiv:2302.09565

Optimizing YOLOv7 for Semiconductor Defect Detection

The field of object detection using Deep Learning (DL) is constantly evolving with many new techniques and models being proposed. YOLOv7 is a state-of-the-art object detector based on the YOLO family of models which have become popular for industrial applications. One such possible application domain can be semiconductor defect inspection. The performance of any machine learning model depends on its hyperparameters. Furthermore, combining predictions of one or more models in different ways can also affect performance. In this research, we experiment with YOLOv7, a recently proposed, state-of-the-art object detector, by training and evaluating models with different hyperparameters to investigate which ones improve performance in terms of detection precision for semiconductor line space pattern defects. The base YOLOv7 model with default hyperparameters and Non Maximum Suppression (NMS) prediction combining outperforms all RetinaNet models from previous work in terms of mean Average Precision (mAP). We find that vertically flipping images randomly during training yields a 3% improvement in the mean AP of all defect classes. Other hyperparameter values improved AP only for certain classes compared to the default model. Combining models that achieve the best AP for different defect classes was found to be an effective ensembling strategy. Combining predictions from ensembles using Weighted Box Fusion (WBF) prediction gave the best performance. The best ensemble with WBF improved on the mAP of the default model by 10%.

arXiv:2304.08591

PALF: Pre-Annotation and Camera-LiDAR Late Fusion for the Easy Annotation of Point Clouds

3D object detection has become indispensable in the field of autonomous driving. To date, gratifying breakthroughs have been recorded in 3D object detection research, attributed to deep learning. However, deep learning algorithms are data-driven and require large amounts of annotated point cloud data for training and evaluation. Unlike 2D image labels, annotating point cloud data is difficult due to the limitations of sparsity, irregularity, and low resolution, which requires more manual work, and the annotation efficiency is much lower than 2D image.Therefore, we propose an annotation algorithm for point cloud data, which is pre-annotation and camera-LiDAR late fusion algorithm to easily and accurately annotate. The contributions of this study are as follows. We propose (1) a pre-annotation algorithm that employs 3D object detection and auto fitting for the easy annotation of point clouds, (2) a camera-LiDAR late fusion algorithm using 2D and 3D results for easily error checking, which helps annotators easily identify missing objects, and (3) a point cloud annotation evaluation pipeline to evaluate our experiments. The experimental results show that the proposed algorithm improves the annotating speed by 6.5 times and the annotation quality in terms of the 3D Intersection over Union and precision by 8.2 points and 5.6 points, respectively; additionally, the miss rate is reduced by 31.9 points.

arXiv:2308.02356공식 코드 · Papers with Code

T-UNet: Triplet UNet for Change Detection in High-Resolution Remote Sensing Images

Remote sensing image change detection aims to identify the differences between images acquired at different times in the same area. It is widely used in land management, environmental monitoring, disaster assessment and other fields. Currently, most change detection methods are based on Siamese network structure or early fusion structure. Siamese structure focuses on extracting object features at different times but lacks attention to change information, which leads to false alarms and missed detections. Early fusion (EF) structure focuses on extracting features after the fusion of images of different phases but ignores the significance of object features at different times for detecting change details, making it difficult to accurately discern the edges of changed objects. To address these issues and obtain more accurate results, we propose a novel network, Triplet UNet(T-UNet), based on a three-branch encoder, which is capable to simultaneously extract the object features and the change features between the pre- and post-time-phase images through triplet encoder. To effectively interact and fuse the features extracted from the three branches of triplet encoder, we propose a multi-branch spatial-spectral cross-attention module (MBSSCA). In the decoder stage, we introduce the channel attention mechanism (CAM) and spatial attention mechanism (SAM) to fully mine and integrate detailed textures information at the shallow layer and semantic localization information at the deep layer.

arXiv:2203.15076

Neurosymbolic hybrid approach to driver collision warning

There are two main algorithmic approaches to autonomous driving systems: (1) An end-to-end system in which a single deep neural network learns to map sensory input directly into appropriate warning and driving responses. (2) A mediated hybrid recognition system in which a system is created by combining independent modules that detect each semantic feature. While some researchers believe that deep learning can solve any problem, others believe that a more engineered and symbolic approach is needed to cope with complex environments with less data. Deep learning alone has achieved state-of-the-art results in many areas, from complex gameplay to predicting protein structures. In particular, in image classification and recognition, deep learning models have achieved accuracies as high as humans. But sometimes it can be very difficult to debug if the deep learning model doesn't work. Deep learning models can be vulnerable and are very sensitive to changes in data distribution. Generalization can be problematic. It's usually hard to prove why it works or doesn't. Deep learning models can also be vulnerable to adversarial attacks. Here, we combine deep learning-based object recognition and tracking with an adaptive neurosymbolic network agent, called the Non-Axiomatic Reasoning System (NARS), that can adapt to its environment by building concepts based on perceptual sequences. We achieved an improved intersection-over-union (IOU) object recognition performance of 0.65 in the adaptive retraining model compared to IOU 0.31 in the COCO data pre-trained model. We improved the object detection limits using RADAR sensors in a simulated environment, and demonstrated the weaving car detection capability by combining deep learning-based object detection and tracking with a neurosymbolic model.

arXiv:1711.10069

Particle filter re-detection for visual tracking via correlation filters

Most of the correlation filter based tracking algorithms can achieve good performance and maintain fast computational speed. However, in some complicated tracking scenes, there is a fatal defect that causes the object to be located inaccurately. In order to address this problem, we propose a particle filter redetection based tracking approach for accurate object localization. During the tracking process, the kernelized correlation filter (KCF) based tracker locates the object by relying on the maximum response value of the response map; when the response map becomes ambiguous, the KCF tracking result becomes unreliable. Our method can provide more candidates by particle resampling to detect the object accordingly. Additionally, we give a new object scale evaluation mechanism, which merely considers the differences between the maximum response values in consecutive frames. Extensive experiments on OTB2013 and OTB2015 datasets demonstrate that the proposed tracker performs favorably in relation to the state-of-the-art methods.

arXiv:2006.04343

Deep Neural Network Based Real-time Kiwi Fruit Flower Detection in an Orchard Environment

In this paper, we present a novel approach to kiwi fruit flower detection using Deep Neural Networks (DNNs) to build an accurate, fast, and robust autonomous pollination robot system. Recent work in deep neural networks has shown outstanding performance on object detection tasks in many areas. Inspired this, we aim for exploiting DNNs for kiwi fruit flower detection and present intensive experiments and their analysis on two state-of-the-art object detectors; Faster R-CNN and Single Shot Detector (SSD) Net, and feature extractors; Inception Net V2 and NAS Net with real-world orchard datasets. We also compare those approaches to find an optimal model which is suitable for a real-time agricultural pollination robot system in terms of accuracy and processing speed. We perform experiments with dataset collected from different seasons and locations (spatio-temporal consistency) in order to demonstrate the performance of the generalized model. The proposed system demonstrates promising results of 0.919, 0.874, and 0.889 for precision, recall, and F1-score respectively on our real-world dataset, and the performance satisfies the requirement for deploying the system onto an autonomous pollination robotics system.

arXiv:2008.05700

What leads to generalization of object proposals?

Object proposal generation is often the first step in many detection models. It is lucrative to train a good proposal model, that generalizes to unseen classes. This could help scaling detection models to larger number of classes with fewer annotations. Motivated by this, we study how a detection model trained on a small set of source classes can provide proposals that generalize to unseen classes. We systematically study the properties of the dataset - visual diversity and label space granularity - required for good generalization. We show the trade-off between using fine-grained labels and coarse labels. We introduce the idea of prototypical classes: a set of sufficient and necessary classes required to train a detection model to obtain generalized proposals in a more data-efficient way. On the Open Images V4 dataset, we show that only 25% of the classes can be selected to form such a prototypical set. The resulting proposals from a model trained with these classes is only 4.3% worse than using all the classes, in terms of average recall (AR). We also demonstrate that Faster R-CNN model leads to better generalization of proposals compared to a single-stage network like RetinaNet.

arXiv:2608.06841v1cs.CV

ECAD: 개체 중심 객체성을 넘어 범주 무관 검출 확장하기

ECAD: Expanding Class-Agnostic Detection Beyond Thing-Centric Objectness

객체 검출(object detection)은 시각적 인지에서 기본적인 작업으로, 인식, 그라운딩(grounding), 추론, 상호작용을 위한 구조화된 영역 표현을 제공합니다. 그러나 기존의 검출 패러다임은 대부분 개체 중심(thing-centric)의 객체성(objectness) 개념을 계승하고 있어, 검출기들은 주로 이산적이고 셀 수 있는 객체 인스턴스를 위치화하도록 학습됩니다. 결과적으로 하늘, 도로, 초원, 물, 운동 경기장과 같은 의미론적으로 유의미한 여러 시각적 요소들은 장면 이해 및 공간 추론에서의 중요성에도 불구하고 배경으로 흡수되는 경우가 많습니다. 본 논문에서는 기존의 개체 중심 객체를 넘어 범주 무관 시각적 후보를 발견하는 것을 목표로 하는 새로운 설정인 확장된 범주 무관 검출(ECAD, Expanded Class-Agnostic Detection)을 공식화합니다. 이러한 설정을 지원하기 위해, 실제 환경과 도메인 간 시나리오를 모두 포괄하며 범주 무관 바운딩 박스 주석이 포함된 '개체 중심 객체성을 넘어선' 벤치마크인 BTCO-Bench를 구축합니다. 나아가 고정된(frozen) DINOv3 인코더 기반의 경량 DETR 기반 검출기인 ECADet을 제안하며, 다양한 시각적 요소에 대한 위치 추정과 객체성 추정을 각각 개선하기 위해 기하학 인지 전문가 회귀(GAER, Geometry-Aware Expert Regression)와 프로토타입 유도 쿼리 변조(PGQM, Prototype-Guided Query Modulation)를 도입합니다. 광범위한 실험을 통해 ECADet이 BTCO-Bench에서 대표적인 범주 무관 및 제안(proposal) 기반 검출기들을 일관되게 능가함을 보여주며, 확장된 객체성 발견의 효과를 입증합니다. 코드와 벤치마크는 공개될 예정입니다.

arXiv:1901.02237

3D Object Detection Using Scale Invariant and Feature Reweighting Networks

3D object detection plays an important role in a large number of real-world applications. It requires us to estimate the localizations and the orientations of 3D objects in real scenes. In this paper, we present a new network architecture which focuses on utilizing the front view images and frustum point clouds to generate 3D detection results. On the one hand, a PointSIFT module is utilized to improve the performance of 3D segmentation. It can capture the information from different orientations in space and the robustness to different scale shapes. On the other hand, our network obtains the useful features and suppresses the features with less information by a SENet module. This module reweights channel features and estimates the 3D bounding boxes more effectively. Our method is evaluated on both KITTI dataset for outdoor scenes and SUN-RGBD dataset for indoor scenes. The experimental results illustrate that our method achieves better performance than the state-of-the-art methods especially when point clouds are highly sparse.