PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2208.00598

A Real-time Edge-AI System for Reef Surveys

Crown-of-Thorn Starfish (COTS) outbreaks are a major cause of coral loss on the Great Barrier Reef (GBR) and substantial surveillance and control programs are ongoing to manage COTS populations to ecologically sustainable levels. In this paper, we present a comprehensive real-time machine learning-based underwater data collection and curation system on edge devices for COTS monitoring. In particular, we leverage the power of deep learning-based object detection techniques, and propose a resource-efficient COTS detector that performs detection inferences on the edge device to assist marine experts with COTS identification during the data collection phase. The preliminary results show that several strategies for improving computational efficiency (e.g., batch-wise processing, frame skipping, model input size) can be combined to run the proposed detection model on edge hardware with low resource consumption and low information loss.

arXiv:2301.13592

Priors are Powerful: Improving a Transformer for Multi-camera 3D Detection with 2D Priors

Transfomer-based approaches advance the recent development of multi-camera 3D detection both in academia and industry. In a vanilla transformer architecture, queries are randomly initialised and optimised for the whole dataset, without considering the differences among input frames. In this work, we propose to leverage the predictions from an image backbone, which is often highly optimised for 2D tasks, as priors to the transformer part of a 3D detection network. The method works by (1). augmenting image feature maps with 2D priors, (2). sampling query locations via ray-casting along 2D box centroids, as well as (3). initialising query features with object-level image features. Experimental results shows that 2D priors not only help the model converge faster, but also largely improve the baseline approach by up to 12% in terms of average precision.

arXiv:2306.06893

In-context Cross-Density Adaptation on Noisy Mammogram Abnormalities Detection

This paper investigates the impact of breast density distribution on the generalization performance of deep-learning models on mammography images using the VinDr-Mammo dataset. We explore the use of domain adaptation techniques, specifically Domain Adaptive Object Detection (DAOD) with the Noise Latent Transferability Exploration (NLTE) framework, to improve model performance across breast densities under noisy labeling circumstances. We propose a robust augmentation framework to bridge the domain gap between the source and target inside a dataset. Our results show that DAOD-based methods, along with the proposed augmentation framework, can improve the generalization performance of deep-learning models (+5% overall mAP improvement approximately in our experimental results compared to commonly used detection models). This paper highlights the importance of domain adaptation techniques in medical imaging, particularly in the context of breast density distribution, which is critical in mammography.

arXiv:2608.05858v1cs.CV

형상 인식 기반의 회전 경계 상자(OBB)에서 수평 경계 상자(HBB)로의 변환

Shape-Aware Oriented Bounding Box (OBB) to Horizontal Bounding Box (HBB) Conversion

항공 및 위성 영상에서의 정확한 객체 검출(object detection)은 경계 상자(bounding box) 표현 방식에 크게 의존합니다. 이는 선박이나 항공기와 같이 공간적으로 방향성을 지닌 객체의 경우 특히 두드러집니다. 회전 경계 상자(Oriented Bounding Box, OBB)는 수평 경계 상자(Horizontal Bounding Box, HBB)에 비해 객체에 더 밀착되고 비최대 억제(NMS)에 더 강건하지만, 기존의 OBB에서 HBB로의 후처리 변환 방식들은 불필요한 빈 공간 및 배경 영역을 과도하게 포함하거나 검출 결과에서 유효 데이터를 누락시키는 문제가 있습니다. 본 논문에서는 원격 탐사 영상의 선박 검출을 위해 형상을 인식하는 새로운 OBB-to-HBB 변환 기법을 제안합니다. 이 방법은 선체 형상, 선체 비대도, 경계 상자의 방향성을 활용하여 객체에 더욱 밀착된 축 정렬 HBB 표현을 생성합니다. 제안된 방법은 최소값과 최대값을 사용하는 외곽 HBB(Outer HBB), 면적 등가 HBB(Area Equivalent HBB), GBB 주변화 HBB(GBB Marginalized HBB) 등 세 가지 OBB-to-HBB 변환 베이스라인 방식과 비교 평가되었습니다.

arXiv:2405.10398

Drone-type-Set: Drone types detection benchmark for drone detection and tracking

The Unmanned Aerial Vehicles (UAVs) market has been significantly growing and Considering the availability of drones at low-cost prices the possibility of misusing them, for illegal purposes such as drug trafficking, spying, and terrorist attacks posing high risks to national security, is rising. Therefore, detecting and tracking unauthorized drones to prevent future attacks that threaten lives, facilities, and security, become a necessity. Drone detection can be performed using different sensors, while image-based detection is one of them due to the development of artificial intelligence techniques. However, knowing unauthorized drone types is one of the challenges due to the lack of drone types datasets. For that, in this paper, we provide a dataset of various drones as well as a comparison of recognized object detection models on the proposed dataset including YOLO algorithms with their different versions, like, v3, v4, and v5 along with the Detectronv2. The experimental results of different models are provided along with a description of each method. The collected dataset can be found in https://drive.google.com/drive/folders/1EPOpqlF4vG7hp4MYnfAecVOsdQ2JwBEd?usp=share_link

arXiv:2202.13514공식 코드 · Papers with Code

StrongSORT: Make DeepSORT Great Again

Recently, Multi-Object Tracking (MOT) has attracted rising attention, and accordingly, remarkable progresses have been achieved. However, the existing methods tend to use various basic models (e.g, detector and embedding model), and different training or inference tricks, etc. As a result, the construction of a good baseline for a fair comparison is essential. In this paper, a classic tracker, i.e., DeepSORT, is first revisited, and then is significantly improved from multiple perspectives such as object detection, feature embedding, and trajectory association. The proposed tracker, named StrongSORT, contributes a strong and fair baseline for the MOT community. Moreover, two lightweight and plug-and-play algorithms are proposed to address two inherent "missing" problems of MOT: missing association and missing detection. Specifically, unlike most methods, which associate short tracklets into complete trajectories at high computation complexity, we propose an appearance-free link model (AFLink) to perform global association without appearance information, and achieve a good balance between speed and accuracy. Furthermore, we propose a Gaussian-smoothed interpolation (GSI) based on Gaussian process regression to relieve the missing detection. AFLink and GSI can be easily plugged into various trackers with a negligible extra computational cost (1.7 ms and 7.1 ms per image, respectively, on MOT17). Finally, by fusing StrongSORT with AFLink and GSI, the final tracker (StrongSORT++) achieves state-of-the-art results on multiple public benchmarks, i.e., MOT17, MOT20, DanceTrack and KITTI. Codes are available at https://github.com/dyhBUPT/StrongSORT and https://github.com/open-mmlab/mmtracking.

arXiv:2211.11478공식 코드 · Papers with Code

Background-Mixed Augmentation for Weakly Supervised Change Detection

Change detection (CD) is to decouple object changes (i.e., object missing or appearing) from background changes (i.e., environment variations) like light and season variations in two images captured in the same scene over a long time span, presenting critical applications in disaster management, urban development, etc. In particular, the endless patterns of background changes require detectors to have a high generalization against unseen environment variations, making this task significantly challenging. Recent deep learning-based methods develop novel network architectures or optimization strategies with paired-training examples, which do not handle the generalization issue explicitly and require huge manual pixel-level annotation efforts. In this work, for the first attempt in the CD community, we study the generalization issue of CD from the perspective of data augmentation and develop a novel weakly supervised training algorithm that only needs image-level labels. Different from general augmentation techniques for classification, we propose the background-mixed augmentation that is specifically designed for change detection by augmenting examples under the guidance of a set of background-changing images and letting deep CD models see diverse environment variations. Moreover, we propose the augmented & real data consistency loss that encourages the generalization increase significantly. Our method as a general framework can enhance a wide range of existing deep learning-based detectors. We conduct extensive experiments in two public datasets and enhance four state-of-the-art methods, demonstrating the advantages of our method. We release the code at https://github.com/tsingqguo/bgmix.

arXiv:1708.02002공식 코드 · Papers with Code

Focal Loss for Dense Object Detection

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far. In this paper, we investigate why this is the case. We discover that the extreme foreground-background class imbalance encountered during training of dense detectors is the central cause. We propose to address this class imbalance by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples. Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. To evaluate the effectiveness of our loss, we design and train a simple dense detector we call RetinaNet. Our results show that when trained with the focal loss, RetinaNet is able to match the speed of previous one-stage detectors while surpassing the accuracy of all existing state-of-the-art two-stage detectors. Code is at: https://github.com/facebookresearch/Detectron.

arXiv:1611.09392

Generating Holistic 3D Scene Abstractions for Text-based Image Retrieval

Spatial relationships between objects provide important information for text-based image retrieval. As users are more likely to describe a scene from a real world perspective, using 3D spatial relationships rather than 2D relationships that assume a particular viewing direction, one of the main challenges is to infer the 3D structure that bridges images with users' text descriptions. However, direct inference of 3D structure from images requires learning from large scale annotated data. Since interactions between objects can be reduced to a limited set of atomic spatial relations in 3D, we study the possibility of inferring 3D structure from a text description rather than an image, applying physical relation models to synthesize holistic 3D abstract object layouts satisfying the spatial constraints present in a textual description. We present a generic framework for retrieving images from a textual description of a scene by matching images with these generated abstract object layouts. Images are ranked by matching object detection outputs (bounding boxes) to 2D layout candidates (also represented by bounding boxes) which are obtained by projecting the 3D scenes with sampled camera directions. We validate our approach using public indoor scene datasets and show that our method outperforms baselines built upon object occurrence histograms and learned 2D pairwise relations.

arXiv:2009.07611공식 코드 · Papers with Code

Perceiving Traffic from Aerial Images

Drones or UAVs, equipped with different sensors, have been deployed in many places especially for urban traffic monitoring or last-mile delivery. It provides the ability to control the different aspects of traffic given real-time obeservations, an important pillar for the future of transportation and smart cities. With the increasing use of such machines, many previous state-of-the-art object detectors, who have achieved high performance on front facing cameras, are being used on UAV datasets. When applied to high-resolution aerial images captured from such datasets, they fail to generalize to the wide range of objects' scales. In order to address this limitation, we propose an object detection method called Butterfly Detector that is tailored to detect objects in aerial images. We extend the concept of fields and introduce butterfly fields, a type of composite field that describes the spatial information of output features as well as the scale of the detected object. To overcome occlusion and viewing angle variations that can hinder the localization process, we employ a voting mechanism between related butterfly vectors pointing to the object center. We evaluate our Butterfly Detector on two publicly available UAV datasets (UAVDT and VisDrone2019) and show that it outperforms previous state-of-the-art methods while remaining real-time.

arXiv:2006.11321

AutoOD: Automated Outlier Detection via Curiosity-guided Search and Self-imitation Learning

Outlier detection is an important data mining task with numerous practical applications such as intrusion detection, credit card fraud detection, and video surveillance. However, given a specific complicated task with big data, the process of building a powerful deep learning based system for outlier detection still highly relies on human expertise and laboring trials. Although Neural Architecture Search (NAS) has shown its promise in discovering effective deep architectures in various domains, such as image classification, object detection, and semantic segmentation, contemporary NAS methods are not suitable for outlier detection due to the lack of intrinsic search space, unstable search process, and low sample efficiency. To bridge the gap, in this paper, we propose AutoOD, an automated outlier detection framework, which aims to search for an optimal neural network model within a predefined search space. Specifically, we firstly design a curiosity-guided search strategy to overcome the curse of local optimality. A controller, which acts as a search agent, is encouraged to take actions to maximize the information gain about the controller's internal belief. We further introduce an experience replay mechanism based on self-imitation learning to improve the sample efficiency. Experimental results on various real-world benchmark datasets demonstrate that the deep model identified by AutoOD achieves the best performance, comparing with existing handcrafted models and traditional search methods.

arXiv:2408.08888공식 코드 · Papers with Code

A Classifier-Based Approach to Multi-Class Anomaly Detection Applied to Astronomical Time-Series

Automating anomaly detection is an open problem in many scientific fields, particularly in time-domain astronomy, where modern telescopes generate millions of alerts per night. Currently, most anomaly detection algorithms for astronomical time-series rely either on hand-crafted features or on features generated through unsupervised representation learning, coupled with standard anomaly detection algorithms. In this work, we introduce a novel approach that leverages the latent space of a neural network classifier for anomaly detection. We then propose a new method called Multi-Class Isolation Forests (MCIF), which trains separate isolation forests for each class to derive an anomaly score for an object based on its latent space representation. This approach significantly outperforms a standard isolation forest when distinct clusters exist in the latent space. Using a simulated dataset emulating the Zwicky Transient Facility (54 anomalies and 12,040 common), our anomaly detection pipeline discovered $46\pm3$ anomalies ($\sim 85\%$ recall) after following up the top 2,000 ($\sim 15\%$) ranked objects. Furthermore, our classifier-based approach outperforms or approaches the performance of other state-of-the-art anomaly detection pipelines. Our novel method demonstrates that existing and new classifiers can be effectively repurposed for real-time anomaly detection. The code used in this work, including a Python package, is publicly available, https://github.com/Rithwik-G/AstroMCAD.

arXiv:2005.08641

Deep Learning Based Vehicle Tracking System Using License Plate Detection And Recognition

Vehicle tracking is an integral part of intelligent traffic management systems. Previous implementations of vehicle tracking used Global Positioning System(GPS) based systems that gave location of the vehicle of an individual on their smartphones.The proposed system uses a novel approach to vehicle tracking using Vehicle License plate detection and recognition (VLPR) technique, which can be integrated on a large scale with traffic management systems. Initial methods of implementing VLPR used simple image processing techniques which were quite experimental and heuristic. With the onset of Deep learning and Computer Vision, one can create robust VLPR systems that can produce results close to human efficiency. Previous implementations, based on deep learning, made use of object detection and support vector machines for detection and a heuristic image processing based approach for recognition. The proposed system makes use of scene text detection model architecture for License plate detection and for recognition it uses the Optical character recognition engine (OCR) Tesseract. The proposed system obtained extraordinary results when it was tested on a highway video using NVIDIA Ge-force RTX 2080ti GPU, results were obtained at a speed of 30 frames per second with accuracy close to human.

arXiv:2309.00775

Contrastive Feature Masking Open-Vocabulary Vision Transformer

We present Contrastive Feature Masking Vision Transformer (CFM-ViT) - an image-text pretraining methodology that achieves simultaneous learning of image- and region-level representation for open-vocabulary object detection (OVD). Our approach combines the masked autoencoder (MAE) objective into the contrastive learning objective to improve the representation for localization tasks. Unlike standard MAE, we perform reconstruction in the joint image-text embedding space, rather than the pixel space as is customary with the classical MAE method, which causes the model to better learn region-level semantics. Moreover, we introduce Positional Embedding Dropout (PED) to address scale variation between image-text pretraining and detection finetuning by randomly dropping out the positional embeddings during pretraining. PED improves detection performance and enables the use of a frozen ViT backbone as a region classifier, preventing the forgetting of open-vocabulary knowledge during detection finetuning. On LVIS open-vocabulary detection benchmark, CFM-ViT achieves a state-of-the-art 33.9 AP$r$, surpassing the best approach by 7.6 points and achieves better zero-shot detection transfer. Finally, CFM-ViT acquires strong image-level representation, outperforming the state of the art on 8 out of 12 metrics on zero-shot image-text retrieval benchmarks.

arXiv:2310.04662공식 코드 · Papers with Code

HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information

A powerful way to adapt a visual recognition model to a new domain is through image translation. However, common image translation approaches only focus on generating data from the same distribution as the target domain. Given a cross-modal application, such as pedestrian detection from aerial images, with a considerable shift in data distribution between infrared (IR) to visible (RGB) images, a translation focused on generation might lead to poor performance as the loss focuses on irrelevant details for the task. In this paper, we propose HalluciDet, an IR-RGB image translation model for object detection. Instead of focusing on reconstructing the original image on the IR modality, it seeks to reduce the detection loss of an RGB detector, and therefore avoids the need to access RGB data. This model produces a new image representation that enhances objects of interest in the scene and greatly improves detection performance. We empirically compare our approach against state-of-the-art methods for image translation and for fine-tuning on IR, and show that our HalluciDet improves detection accuracy in most cases by exploiting the privileged information encoded in a pre-trained RGB detector. Code: https://github.com/heitorrapela/HalluciDet

arXiv:2111.10971공식 코드 · Papers with Code

Tracking Grow-Finish Pigs Across Large Pens Using Multiple Cameras

Increasing demand for meat products combined with farm labor shortages has resulted in a need to develop new real-time solutions to monitor animals effectively. Significant progress has been made in continuously locating individual pigs using tracking-by-detection methods. However, these methods fail for oblong pens because a single fixed camera does not cover the entire floor at adequate resolution. We address this problem by using multiple cameras, placed such that the visual fields of adjacent cameras overlap, and together they span the entire floor. Avoiding breaks in tracking requires inter-camera handover when a pig crosses from one camera's view into that of an adjacent camera. We identify the adjacent camera and the shared pig location on the floor at the handover time using inter-view homography. Our experiments involve two grow-finish pens, housing 16-17 pigs each, and three RGB cameras. Our algorithm first detects pigs using a deep learning-based object detection model (YOLO) and creates their local tracking IDs using a multi-object tracking algorithm (DeepSORT). We then use inter-camera shared locations to match multiple views and generate a global ID for each pig that holds throughout tracking. To evaluate our approach, we provide five two-minutes long video sequences with fully annotated global identities. We track pigs in a single camera view with a Multi-Object Tracking Accuracy and Precision of 65.0% and 54.3% respectively and achieve a Camera Handover Accuracy of 74.0%. We open-source our code and annotated dataset at https://github.com/AIFARMS/multi-camera-pig-tracking

arXiv:2609.26919v1cs.RO

시계를 굽히다: 이벤트 기반 객체 검출에서 지연을 이기 위한 선행 예측

Bend the Clock: Predicting Ahead to Beat Latency in Event-Based Object Detection

이벤트 카메라는 고속 로봇 시스템에서 낮은 지연의 인지를 약속하지만, 짧은 지연조차도 검출 결과가 하위 로봇 의사결정에 반영될 때쯤에는 이미 낡은 정보가 될 수 있다. 그럼에도 최신 이벤트 검출기는 예측이 사용 가능해지기까지 수십 밀리초의 연산을 여전히 요구한다. 기존 평가는 관측 시각의 주석과 예측을 비교하여 이 지연을 무시하는데, 실제로는 그 예측이 생성될 때쯤 장면이 이미 바뀌었을 수 있다. 본 연구는 이벤트 기반 다중 객체 검출에서 이러한 관측–가용성 불일치를 분석하고, 최신 이벤트 검출기가 관측 시각이 아니라 예측 가용 시각 기준으로 평가할 때 성능이 크게 저하됨을 보인다. 이를 해결하기 위해 ChronoFuse를 제안한다. ChronoFuse는 입력이 관측된 시각이 아니라 출력이 사용 가능해지는 시각의 객체 상태를 예측하는 인과적 가용-시각 검출기이다. ChronoFuse는 다중 스케일 특징 계층에 걸친 인과적 교차-시간 융합을 수행하여, 캐시된 시간적 특징과 현재 표현을 결합함으로써 미래 관측을 사용하지 않고 단기 시간적 단서를 드러낸다. 융합 경로는 경량이며, 평균 end-to-end 지연 오버헤드는 0.17백만 개의 파라미터와 0.84 ms만 추가한다. ChronoFuse는 1Mpx 주행 데이터에서 지연으로 인한 정확도 손실의 71%를 회복하고, FRED의 급격한 드론 움직임에서는 90.8%를 회복하여 거의 무지연 성능에 가깝게 복원한다. EV-Flying의 극한적인 움직임에서는 ChronoFuse가 20.95 sAP에 도달하며, 가장 강한 표준 이벤트 검출기의 2.25 대비 9.3배 향상을 보인다. 이 결과는 자율주행, 민첩 비행, 로봇 요격 등 빠르게 변하는 장면에서 동작하는 로봇에게 선행 예측이 핵심적일 수 있음을 보여준다.

arXiv:1910.11713공식 코드 · Papers with Code

ALET (Automated Labeling of Equipment and Tools): A Dataset, a Baseline and a Usecase for Tool Detection in the Wild

Robots collaborating with humans in realistic environments will need to be able to detect the tools that can be used and manipulated. However, there is no available dataset or study that addresses this challenge in real settings. In this paper, we fill this gap by providing an extensive dataset (METU-ALET) for detecting farming, gardening, office, stonemasonry, vehicle, woodworking and workshop tools. The scenes correspond to sophisticated environments with or without humans using the tools. The scenes we consider introduce several challenges for object detection, including the small scale of the tools, their articulated nature, occlusion, inter-class invariance, etc. Moreover, we train and compare several state of the art deep object detectors (including Faster R-CNN, Cascade R-CNN, RepPoint and RetinaNet) on our dataset. We observe that the detectors have difficulty in detecting especially small-scale tools or tools that are visually similar to parts of other tools. This in turn supports the importance of our dataset and paper. With the dataset, the code and the trained models, our work provides a basis for further research into tools and their use in robotics applications.

arXiv:2012.03265공식 코드 · Papers with Code

Towards Better Object Detection in Scale Variation with Adaptive Feature Selection

It is a common practice to exploit pyramidal feature representation to tackle the problem of scale variation in object instances. However, most of them still predict the objects in a certain range of scales based solely or mainly on a single-level representation, yielding inferior detection performance. To this end, we propose a novel adaptive feature selection module (AFSM), to automatically learn the way to fuse multi-level representations in the channel dimension, in a data-driven manner. It significantly improves the performance of the detectors that have a feature pyramid structure, while introducing nearly free inference overhead. Moreover, a class-aware sampling mechanism (CASM) is proposed to tackle the class imbalance problem, by re-weighting the sampling ratio to each of the training images, based on the statistical characteristics of each class. This is crucial to improve the performance of the minor classes. Experimental results demonstrate the effectiveness of the proposed method, with 83.04% mAP at 15.96 FPS on the VOC dataset, and 39.48% AP on the VisDrone-DET validation subset, respectively, outperforming other state-of-the-art detectors considerably. The code is available at https://github.com/ZeHuiGong/AFSM.git.

arXiv:2109.02552

Joint Multi-User Communication and Sensing Exploiting Both Signal and Environment Sparsity

As a potential technology feature for 6G wireless networks, the idea of sensing-communication integration requires the system not only to complete reliable multi-user communication but also to achieve accurate environment sensing. In this paper, we consider such a joint communication and sensing (JCAS) scenario, in which multiple users use the sparse code multiple access (SCMA) scheme to communicate with the wireless access point (AP). Part of the user signals are scattered by the environment object and reflected by an intelligent reflective surface (IRS) before they arrive at the AP. We exploit the sparsity of both the structured user signals and the unstructured environment and propose an iterative and incremental joint multi-user communication and environment sensing scheme, in which the two processes, i.e., multi-user information detection and environment object detection, interweave with each other thanks to their intrinsic mutual dependence. The proposed algorithm is sliding-window based and also graph based, which can keep on sensing the environment as long as there are illuminating user signals. The trade-off relationship between the key system parameters is analyzed, and the simulation result validates the convergence and effectiveness of the proposed algorithm.