PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2304.09694

CrossFusion: Interleaving Cross-modal Complementation for Noise-resistant 3D Object Detection

The combination of LiDAR and camera modalities is proven to be necessary and typical for 3D object detection according to recent studies. Existing fusion strategies tend to overly rely on the LiDAR modal in essence, which exploits the abundant semantics from the camera sensor insufficiently. However, existing methods cannot rely on information from other modalities because the corruption of LiDAR features results in a large domain gap. Following this, we propose CrossFusion, a more robust and noise-resistant scheme that makes full use of the camera and LiDAR features with the designed cross-modal complementation strategy. Extensive experiments we conducted show that our method not only outperforms the state-of-the-art methods under the setting without introducing an extra depth estimation network but also demonstrates our model's noise resistance without re-training for the specific malfunction scenarios by increasing 5.2\% mAP and 2.4\% NDS.

arXiv:2306.16798

Evaluation of Environmental Conditions on Object Detection using Oriented Bounding Boxes for AR Applications

The objective of augmented reality (AR) is to add digital content to natural images and videos to create an interactive experience between the user and the environment. Scene analysis and object recognition play a crucial role in AR, as they must be performed quickly and accurately. In this study, a new approach is proposed that involves using oriented bounding boxes with a detection and recognition deep network to improve performance and processing time. The approach is evaluated using two datasets: a real image dataset (DOTA dataset) commonly used for computer vision tasks, and a synthetic dataset that simulates different environmental, lighting, and acquisition conditions. The focus of the evaluation is on small objects, which are difficult to detect and recognise. The results indicate that the proposed approach tends to produce better Average Precision and greater accuracy for small objects in most of the tested conditions.

arXiv:2411.17006공식 코드 · Papers with Code

Event-based Spiking Neural Networks for Object Detection: A Review of Datasets, Architectures, Learning Rules, and Implementation

Spiking Neural Networks (SNNs) represent a biologically inspired paradigm offering an energy-efficient alternative to conventional artificial neural networks (ANNs) for Computer Vision (CV) applications. This paper presents a systematic review of datasets, architectures, learning methods, implementation techniques, and evaluation methodologies used in CV-based object detection tasks using SNNs. Based on an analysis of 151 journal and conference articles, the review codifies: 1) the effectiveness of fully connected, convolutional, and recurrent architectures; 2) the performance of direct unsupervised, direct supervised, and indirect learning methods; and 3) the trade-offs in energy consumption, latency, and memory in neuromorphic hardware implementations. An open-source repository along with detailed examples of Python code and resources for building SNN models, event-based data processing, and SNN simulations are provided. Key challenges in SNN training, hardware integration, and future directions for CV applications are also identified.

arXiv:1607.03333

RGBD Salient Object Detection via Deep Fusion

Numerous efforts have been made to design different low level saliency cues for the RGBD saliency detection, such as color or depth contrast features, background and color compactness priors. However, how these saliency cues interact with each other and how to incorporate these low level saliency cues effectively to generate a master saliency map remain a challenging problem. In this paper, we design a new convolutional neural network (CNN) to fuse different low level saliency cues into hierarchical features for automatically detecting salient objects in RGBD images. In contrast to the existing works that directly feed raw image pixels to the CNN, the proposed method takes advantage of the knowledge in traditional saliency detection by adopting various meaningful and well-designed saliency feature vectors as input. This can guide the training of CNN towards detecting salient object more effectively due to the reduced learning ambiguity. We then integrate a Laplacian propagation framework with the learned CNN to extract a spatially consistent saliency map by exploiting the intrinsic structure of the input image. Extensive quantitative and qualitative experimental evaluations on three datasets demonstrate that the proposed method consistently outperforms state-of-the-art methods.

arXiv:2205.09592

Transferable Physical Attack against Object Detection with Separable Attention

Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability to unseen models, thus leading to the poor performance of black-box attack.In this paper, we put forward a novel method of generating physically realizable adversarial camouflage to achieve transferable attack against detection models. More specifically, we first introduce multi-scale attention maps based on detection models to capture features of objects with various resolutions. Meanwhile, we adopt a sequence of composite transformations to obtain the averaged attention maps, which could curb model-specific noise in the attention and thus further boost transferability. Unlike the general visualization interpretation methods where model attention should be put on the foreground object as much as possible, we carry out attack on separable attention from the opposite perspective, i.e. suppressing attention of the foreground and enhancing that of the background. Consequently, transferable adversarial camouflage could be yielded efficiently with our novel attention-based loss function. Extensive comparison experiments verify the superiority of our method to state-of-the-art methods.

arXiv:1711.02441

A Survey on Hardware Implementations of Visual Object Trackers

Visual object tracking is an active topic in the computer vision domain with applications extending over numerous fields. The main sub-tasks required to build an object tracker (e.g. object detection, feature extraction and object tracking) are computation-intensive. In addition, real-time operation of the tracker is indispensable for almost all of its applications. Therefore, complete hardware or hardware/software co-design approaches are pursued for better tracker implementations. This paper presents a literature survey of the hardware implementations of object trackers over the last two decades. Although several tracking surveys exist in literature, a survey addressing the hardware implementations of the different trackers is missing. We believe this survey would fill the gap and complete the picture with the existing surveys of how to design an efficient tracker and point out the future directions researchers can follow in this field. We highlight the lack of hardware implementations for state-of-the-art tracking algorithms as well as for enhanced classical algorithms. We also stress the need for measuring the tracking performance of the hardware-based trackers. Additionally, enough details of the hardware-based trackers need to be provided to allow reasonable comparison between the different implementations.

arXiv:1603.09446

Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputs

Object skeleton is a useful cue for object detection, complementary to the object contour, as it provides a structural representation to describe the relationship among object parts. While object skeleton extraction in natural images is a very challenging problem, as it requires the extractor to be able to capture both local and global image context to determine the intrinsic scale of each skeleton pixel. Existing methods rely on per-pixel based multi-scale feature computation, which results in difficult modeling and high time consumption. In this paper, we present a fully convolutional network with multiple scale-associated side outputs to address this problem. By observing the relationship between the receptive field sizes of the sequential stages in the network and the skeleton scales they can capture, we introduce a scale-associated side output to each stage. We impose supervision to different stages by guiding the scale-associated side outputs toward groundtruth skeletons of different scales. The responses of the multiple scale-associated side outputs are then fused in a scale-specific way to localize skeleton pixels with multiple scales effectively. Our method achieves promising results on two skeleton extraction datasets, and significantly outperforms other competitors.

arXiv:1811.09561

An Adaptive Approach for Automated Grapevine Phenotyping using VGG-based Convolutional Neural Networks

In (grapevine) breeding programs and research, periodic phenotyping and multi-year monitoring of different grapevine traits, like growth or yield, is needed especially in the field. This demand imply objective, precise and automated methods using sensors and adaptive software. This work presents a proof-of-concept analyzing RGB images of different growth stages of grapevines with the aim to detect and quantify promising plant organs which are related to yield. The input images are segmented by a Fully Convolutional Neural Network (FCN) into object and background pixels. The objects are plant organs like young shoots, pedicels, flower buds or grapes, which are principally suitable for yield estimation. In the ground truth of the training images, each object is separately annotated as a connected segment of object pixels, which enables end-to-end learning of the object features. Based on the CNN-based segmentation, the number of objects is determined by detecting and counting connected components of object pixels using region labeling. In an evaluation on six different data sets, the system achieves an IoU of up to 87.3% for the segmentation and an F1 score of up to 88.6% for the object detection.

arXiv:2203.14272공식 코드 · Papers with Code

Discovering Human-Object Interaction Concepts via Self-Compositional Learning

A comprehensive understanding of human-object interaction (HOI) requires detecting not only a small portion of predefined HOI concepts (or categories) but also other reasonable HOI concepts, while current approaches usually fail to explore a huge portion of unknown HOI concepts (i.e., unknown but reasonable combinations of verbs and objects). In this paper, 1) we introduce a novel and challenging task for a comprehensive HOI understanding, which is termed as HOI Concept Discovery; and 2) we devise a self-compositional learning framework (or SCL) for HOI concept discovery. Specifically, we maintain an online updated concept confidence matrix during training: 1) we assign pseudo-labels for all composite HOI instances according to the concept confidence matrix for self-training; and 2) we update the concept confidence matrix using the predictions of all composite HOI instances. Therefore, the proposed method enables the learning on both known and unknown HOI concepts. We perform extensive experiments on several popular HOI datasets to demonstrate the effectiveness of the proposed method for HOI concept discovery, object affordance recognition and HOI detection. For example, the proposed self-compositional learning framework significantly improves the performance of 1) HOI concept discovery by over 10% on HICO-DET and over 3% on V-COCO, respectively; 2) object affordance recognition by over 9% mAP on MS-COCO and HICO-DET; and 3) rare-first and non-rare-first unknown HOI detection relatively over 30% and 20%, respectively. Code is publicly available at https://github.com/zhihou7/HOI-CL.

arXiv:2112.05410

Multimedia Datasets for Anomaly Detection: A Review

Multimedia anomaly datasets play a crucial role in automated surveillance. They have a wide range of applications expanding from outlier objects/ situation detection to the detection of life-threatening events. For more than 1.5 decades, this field has attracted a lot of research attention, and as a result, more and more datasets dedicated to anomalous actions and object detection have been developed. Tapping these public anomaly datasets enable researchers to generate and compare various anomaly detection frameworks with the same input data. This paper presents a comprehensive survey on a variety of video, audio, as well as audio-visual datasets based on the application of anomaly detection. This survey aims to address the lack of a comprehensive comparison and analysis of multimedia public datasets based on anomaly detection. Also, it can assist researchers in selecting the best available dataset for bench-marking frameworks. Additionally, we discuss gaps in the existing dataset and insights for future direction towards developing multimodal anomaly detection datasets.

arXiv:1809.04320

Learning regression and verification networks for long-term visual tracking

Compared with short-term tracking, the long-term tracking task requires determining the tracked object is present or absent, and then estimating the accurate bounding box if present or conducting image-wide re-detection if absent. Until now, few attempts have been done although this task is much closer to designing practical tracking systems. In this work, we propose a novel long-term tracking framework based on deep regression and verification networks. The offline-trained regression model is designed using the object-aware feature fusion and region proposal networks to generate a series of candidates and estimate their similarity scores effectively. The verification network evaluates these candidates to output the optimal one as the tracked object with its classification score, which is online updated to adapt to the appearance variations based on newly reliable observations. The similarity and classification scores are combined to obtain a final confidence value, based on which our tracker can determine the absence of the target accurately and conduct image-wide re-detection to capture the target successfully when it reappears. Extensive experiments show that our tracker achieves the best performance on the VOT2018 long-term challenge and state-of-the-art results on the OxUvA long-term dataset.

arXiv:2208.04171

Object Detection Using Sim2Real Domain Randomization for Robotic Applications

Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for different industrial applications. In this article, we propose a sim2real transfer learning method based on domain randomization for object detection with which labeled synthetic datasets of arbitrary size and object types can be automatically generated. Subsequently, a state-of-the-art convolutional neural network, YOLOv4, is trained to detect the different types of industrial objects. With the proposed domain randomization method, we could shrink the reality gap to a satisfactory level, achieving 86.32% and 97.38% mAP50 scores, respectively, in the case of zero-shot and one-shot transfers, on our manually annotated dataset containing 190 real images. Our solution fits for industrial use as the data generation process takes less than 0.5 s per image and the training lasts only around 12 h, on a GeForce RTX 2080 Ti GPU. Furthermore, it can reliably differentiate similar classes of objects by having access to only one real image for training. To our best knowledge, this is the only work thus far satisfying these constraints.

arXiv:2307.13654

Personal Protective Equipment Detection in Extreme Construction Conditions

Object detection has been widely applied for construction safety management, especially personal protective equipment (PPE) detection. Though the existing PPE detection models trained on conventional datasets have achieved excellent results, their performance dramatically declines in extreme construction conditions. A robust detection model NST-YOLOv5 is developed by combining the neural style transfer (NST) and YOLOv5 technologies. Five extreme conditions are considered and simulated via the NST module to endow the detection model with excellent robustness, including low light, intense light, sand dust, fog, and rain. Experiments show that the NST has great potential as a tool for extreme data synthesis since it is better at simulating extreme conditions than other traditional image processing algorithms and helps the NST-YOLOv5 achieve 0.141 and 0.083 mAP_(05:95) improvements in synthesized and real-world extreme data. This study provides a new feasible way to obtain a more robust detection model for extreme construction conditions.

arXiv:2209.03102공식 코드 · Papers with Code

MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection

Fusing LiDAR and camera information is essential for achieving accurate and reliable 3D object detection in autonomous driving systems. This is challenging due to the difficulty of combining multi-granularity geometric and semantic features from two drastically different modalities. Recent approaches aim at exploring the semantic densities of camera features through lifting points in 2D camera images (referred to as seeds) into 3D space, and then incorporate 2D semantics via cross-modal interaction or fusion techniques. However, depth information is under-investigated in these approaches when lifting points into 3D space, thus 2D semantics can not be reliably fused with 3D points. Moreover, their multi-modal fusion strategy, which is implemented as concatenation or attention, either can not effectively fuse 2D and 3D information or is unable to perform fine-grained interactions in the voxel space. To this end, we propose a novel framework with better utilization of the depth information and fine-grained cross-modal interaction between LiDAR and camera, which consists of two important components. First, a Multi-Depth Unprojection (MDU) method with depth-aware designs is used to enhance the depth quality of the lifted points at each interaction level. Second, a Gated Modality-Aware Convolution (GMA-Conv) block is applied to modulate voxels involved with the camera modality in a fine-grained manner and then aggregate multi-modal features into a unified space. Together they provide the detection head with more comprehensive features from LiDAR and camera. On the nuScenes test benchmark, our proposed method, abbreviated as MSMDFusion, achieves state-of-the-art 3D object detection results with 71.5% mAP and 74.0% NDS, and strong tracking results with 74.0% AMOTA without using test-time-augmentation and ensemble techniques. The code is available at https://github.com/SxJyJay/MSMDFusion.

arXiv:2412.15595

Mask-RadarNet: Enhancing Transformer With Spatial-Temporal Semantic Context for Radar Object Detection in Autonomous Driving

As a cost-effective and robust technology, automotive radar has seen steady improvement during the last years, making it an appealing complement to commonly used sensors like camera and LiDAR in autonomous driving. Radio frequency data with rich semantic information are attracting more and more attention. Most current radar-based models take radio frequency image sequences as the input. However, these models heavily rely on convolutional neural networks and leave out the spatial-temporal semantic context during the encoding stage. To solve these problems, we propose a model called Mask-RadarNet to fully utilize the hierarchical semantic features from the input radar data. Mask-RadarNet exploits the combination of interleaved convolution and attention operations to replace the traditional architecture in transformer-based models. In addition, patch shift is introduced to the Mask-RadarNet for efficient spatial-temporal feature learning. By shifting part of patches with a specific mosaic pattern in the temporal dimension, Mask-RadarNet achieves competitive performance while reducing the computational burden of the spatial-temporal modeling. In order to capture the spatial-temporal semantic contextual information, we design the class masking attention module (CMAM) in our encoder. Moreover, a lightweight auxiliary decoder is added to our model to aggregate prior maps generated from the CMAM. Experiments on the CRUW dataset demonstrate the superiority of the proposed method to some state-of-the-art radar-based object detection algorithms. With relatively lower computational complexity and fewer parameters, the proposed Mask-RadarNet achieves higher recognition accuracy for object detection in autonomous driving.

arXiv:2010.01202

Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-Ray Images

Recently, progress has been made in the supervised training of Convolutional Object Detectors (e.g. Faster R-CNN) for threat recognition in carry-on luggage using X-ray images. This is part of the Transportation Security Administration's (TSA's) mission to protect air travelers in the United States. While more training data with threats may reliably improve performance for this class of deep algorithm, it is expensive to stage in realistic contexts. By contrast, data from the real world can be collected quickly with minimal cost. In this paper, we present a semi-supervised approach for threat recognition which we call Background Adaptive Faster R-CNN. This approach is a training method for two-stage object detectors which uses Domain Adaptation methods from the field of deep learning. The data sources described earlier make two "domains": a hand-collected data domain of images with threats, and a real-world domain of images assumed without threats. Two domain discriminators, one for discriminating object proposals and one for image features, are adversarially trained to prevent encoding domain-specific information. Without this penalty a Convolutional Neural Network (CNN) can learn to identify domains based on superficial characteristics, and minimize a supervised loss function without improving its ability to recognize objects. For the hand-collected data, only object proposals and image features from backgrounds are used. The losses for these domain-adaptive discriminators are added to the Faster R-CNN losses of images from both domains. This can reduce threat detection false alarm rates by matching the statistics of extracted features from hand-collected backgrounds to real world data. Performance improvements are demonstrated on two independently-collected datasets of labeled threats.

arXiv:2310.17875공식 코드 · Papers with Code

Siamese-DETR for Generic Multi-Object Tracking

The ability to detect and track the dynamic objects in different scenes is fundamental to real-world applications, e.g., autonomous driving and robot navigation. However, traditional Multi-Object Tracking (MOT) is limited to tracking objects belonging to the pre-defined closed-set categories. Recently, Open-Vocabulary MOT (OVMOT) and Generic MOT (GMOT) are proposed to track interested objects beyond pre-defined categories with the given text prompt and template image. However, the expensive well pre-trained (vision-)language model and fine-grained category annotations are required to train OVMOT models. In this paper, we focus on GMOT and propose a simple but effective method, Siamese-DETR, for GMOT. Only the commonly used detection datasets (e.g., COCO) are required for training. Different from existing GMOT methods, which train a Single Object Tracking (SOT) based detector to detect interested objects and then apply a data association based MOT tracker to get the trajectories, we leverage the inherent object queries in DETR variants. Specifically: 1) The multi-scale object queries are designed based on the given template image, which are effective for detecting different scales of objects with the same category as the template image; 2) A dynamic matching training strategy is introduced to train Siamese-DETR on commonly used detection datasets, which takes full advantage of provided annotations; 3) The online tracking pipeline is simplified through a tracking-by-query manner by incorporating the tracked boxes in previous frame as additional query boxes. The complex data association is replaced with the much simpler Non-Maximum Suppression (NMS). Extensive experimental results show that Siamese-DETR surpasses existing MOT methods on GMOT-40 dataset by a large margin. Codes are avaliable at \url{https://github.com/yumu-173/Siamese-DETR}.

arXiv:2611.16742v1cs.CV

Fog-FWL: 안개에 가려진 물체 복원을 위한 대규모 풀 웨이브폼 LiDAR 데이터셋

Fog-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Recovering Fog-Hidden Objects

LiDAR는 자율주행의 핵심 센서이지만 안개에 매우 취약하다. 안개 산란은 센서 근처에서 강한 후방 산란을 일으키고 그 뒤에 있는 물체의 반사를 감쇠시키므로, 수신 신호를 포인트 클라우드로 변환하는 피크 검출 과정에서 약한 물체 반환 신호가 흔히 버려진다. 피크 검출 이전의 수신 광신호를 기록하는 풀 웨이브폼 LiDAR(FWL)는 이러한 약한 반환 신호를 보존하지만, 적합한 데이터의 부족으로 FWL로부터 안개에 가려진 물체를 복원하는 연구가 이루어지지 못했다. 본 논문은 이 과제를 위한 데이터셋 기반인 Fog-FWL을 제시하며, 이는 실제 환경 벤치마크인 Fog-FWL-Real과 대규모 합성 학습 세트인 Fog-FWL-Sim으로 구성된다. Fog-FWL-Real은 8개 장면과 58개 시퀀스에서 얻은 7,527개의 실제 안개 FWL 프레임을 포함하며, 이는 기존의 유일한 실제 안개 FWL 데이터보다 579배 크다. 또한 히스토그램 수준의 Object/Fog/Noise 레이블, 10,719개의 3D 바운딩 박스, 물체 반사의 감쇠로 정의된 세 가지 난이도 수준을 함께 제공한다. Fog-FWL-Sim은 공간적으로 불균일한 안개 밀도 장, 다중 산란을 포함한 시간 분해 광 수송, 광자 계수 SPAD 수신기 모델을 통합한 물리 기반 시뮬레이터 Fog-FWL-Simulator로 생성한 12,000개 프레임을 포함한다. 두 부분집합은 동일한 센서 형식과 주석 규약을 공유하므로, 학습에 실제 파형을 전혀 사용하지 않는 엄격한 시뮬레이션-실제 평가가 가능하다. 분석 결과, 가장 어려운 조건에서는 물체 광선의 34.9%에서만 물체 반환 신호가 가장 강한 세 개의 피크에 포함되며, 이는 파형 수준 복원의 필요성을 보여 준다. Fog-FWL-Real, Fog-FWL-Sim, Fog-FWL-Simulator는 안개에 강건한 LiDAR 인식 연구를 촉진하기 위해 공개될 예정이다.

arXiv:2202.02666

Simulation-to-Reality domain adaptation for offline 3D object annotation on pointclouds with correlation alignment

Annotating objects with 3D bounding boxes in LiDAR pointclouds is a costly human driven process in an autonomous driving perception system. In this paper, we present a method to semi-automatically annotate real-world pointclouds collected by deployment vehicles using simulated data. We train a 3D object detector model on labeled simulated data from CARLA jointly with real world pointclouds from our target vehicle. The supervised object detection loss is augmented with a CORAL loss term to reduce the distance between labeled simulated and unlabeled real pointcloud feature representations. The goal here is to learn representations that are invariant to simulated (labeled) and real-world (unlabeled) target domains. We also provide an updated survey on domain adaptation methods for pointclouds.

arXiv:2112.09828공식 코드 · Papers with Code

Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs

Dynamic scene graph generation from a video is challenging due to the temporal dynamics of the scene and the inherent temporal fluctuations of predictions. We hypothesize that capturing long-term temporal dependencies is the key to effective generation of dynamic scene graphs. We propose to learn the long-term dependencies in a video by capturing the object-level consistency and inter-object relationship dynamics over object-level long-term tracklets using transformers. Experimental results demonstrate that our Dynamic Scene Graph Detection Transformer (DSG-DETR) outperforms state-of-the-art methods by a significant margin on the benchmark dataset Action Genome. Our ablation studies validate the effectiveness of each component of the proposed approach. The source code is available at https://github.com/Shengyu-Feng/DSG-DETR.