We investigate the problem of explainability for visual object detectors. Specifically, we demonstrate on the example of the YOLO object detector how to integrate Grad-CAM into the model architecture and analyze the results. We show how to compute attribution-based explanations for individual detections and find that the normalization of the results has a great impact on their interpretation.
FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection
United Arab Emirates University（阿联酋大学）；University at Albany — State University of New York（纽约州立大学奥尔巴尼分校）；National Yang Ming Chiao Tung University（国立阳明交通大学）；Mongolian University of Science and Technology（蒙古科技大学）；National Center for High-Performance Computing（国家高速网络与计算中心）
本文构建开放的 FishEye8K 鱼眼道路目标检测数据集，含 8,000 张图像、157K 个边界框，并评估多种 YOLO 系列 SoTA 模型。
Lidar based 3D object detection and classification tasks are essential for automated driving(AD). A Lidar sensor can provide the 3D point coud data reconstruction of the surrounding environment. But the detection in 3D point cloud still needs a strong algorithmic challenge. This paper consists of three parts.(1)Lidar-camera calib. (2)YOLO, based detection and PointCloud extraction, (3) k-means based point cloud segmentation. In our research, Camera can capture the image to make the Real-time 2D Object Detection by using YOLO, I transfer the bounding box to node whose function is making 3d obje…
Purdue University（普渡大学）；Loyola University Chicago（芝加哥洛约拉大学）；Argonne National Laboratory（阿贡国家实验室）；Intel Corporation（英特尔公司）；Facebook Corporation（脸书公司（Facebook））；School of Electrical and Computer Engineering（电气与计算机工程学院）；Department of Computer Science（计算机科学系）；Argonne Leadership Computing Facility（阿贡领导力计算设施）；Santa Clara（圣克拉拉）；Menlo Park（门洛帕克）；West Lafayette, IN, USA（美国印第安纳州西拉斐特）
Computer vision relies on labeled datasets for training and evaluation in detecting and recognizing objects. The popular computer vision program, YOLO ("You Only Look Once"), has been shown to accurately detect objects in many major image datasets. However, the images found in those datasets, are independent of one another and cannot be used to test YOLO's consistency at detecting the same object as its environment (e.g. ambient lighting) changes. This paper describes a novel effort to evaluate YOLO's consistency for large-scale applications. It does so by working (a) at large scale and (b) by…
University of Galway（戈尔韦大学）；Xperi Corporation（Xperi公司）
Neuromorphic vision or event vision is an advanced vision technology, where in contrast to the visible camera that outputs pixels, the event vision generates neuromorphic events every time there is a brightness change which exceeds a specific threshold in the field of view (FOV). This study focuses on leveraging neuromorphic event data for roadside object detection. This is a proof of concept towards building artificial intelligence (AI) based pipelines which can be used for forward perception systems for advanced vehicular applications. The focus is on building efficient state-of-the-art obje…
Chittagong University of Engineering and Technology（吉大港工程技术大学）
Wrong-way driving is one of the main causes of road accidents and traffic jam all over the world. By detecting wrong-way vehicles, the number of accidents can be minimized and traffic jam can be reduced. With the increasing popularity of real-time traffic management systems and due to the availability of cheaper cameras, the surveillance video has become a big source of data. In this paper, we propose an automatic wrong-way vehicle detection system from on-road surveillance camera footage. Our system works in three stages: the detection of vehicles from the video frame by using the You Only Lo…
University of British Columbia（不列颠哥伦比亚大学）；Agriculture and Agri-Food Canada（加拿大农业与农业食品部）
Tree fruit breeding is a long-term activity involving repeated measurements of various fruit quality traits on a large number of samples. These traits are traditionally measured by manually counting the fruits, weighing to indirectly measure the fruit size, and fruit colour is classified subjectively into different color categories using visual comparison to colour charts. These processes are slow, expensive and subject to evaluators' bias and fatigue. Recent advancements in deep learning can help automate this process. A method was developed to automatically count the number of sweet cherry f…
Graduate School of Interdisciplinary Information Studies, The University of Tokyo（东京大学跨学科信息学研究生院）；National Institute of Advanced Industrial Science and Technology（产业技术综合研究所）
Lidar based 3D object detection and classification tasks are essential for autonomous driving(AD). A lidar sensor can provide the 3D point cloud data reconstruction of the surrounding environment. However, real time detection in 3D point clouds still needs a strong algorithmic. This paper proposes a 3D object detection method based on point cloud and image which consists of there parts.(1)Lidar-camera calibration and undistorted image transformation. (2)YOLO-based detection and PointCloud extraction, (3)K-means based point cloud segmentation and detection experiment test and evaluation in dept…
Performance Optimization of YOLO-FEDER FusionNet for Robust Drone Detection in Visually Complex Environments
Institute for the Protection of Terrestrial Infrastructures, German Aerospace Center（地面基础设施保护研究所，德国航天中心）；ACIDA Lab, University of Applied Sciences Darmstadt（达姆施塔特应用科学大学ACIDA实验室）；European University of Technology（欧洲技术大学）
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Microsoft（微软）；Hong Kong Metropolitan University（香港都会大学）；Lingnan University（岭南大学）；University of Waterloo（滑铁卢大学）
Snow is one of the toughest adverse weather conditions for object detection (OD). Currently, not only there is a lack of snowy OD datasets to train cutting-edge detectors, but also these detectors have difficulties learning latent information beneficial for detection in snow. To alleviate the two above problems, we first establish a real-world snowy OD dataset, named RSOD. Besides, we develop an unsupervised training strategy with a distinctive activation function, called $Peak \ Act$, to quantitatively evaluate the effect of snow on each object. Peak Act helps grading the images in RSOD into …
Henan University of Urban Construction（河南城建学院）；University of North Carolina（北卡罗来纳大学）；Northeast Institute of Geography and Agricultural Ecology, Chinese Academy of Sciences（中国科学院东北地理与农业生态研究所）；Zhengzhou University（郑州大学）
The use of ground control points (GCPs) for georeferencing is the most common strategy in unmanned aerial vehicle (UAV) photogrammetry, but at the same time their collection represents the most time-consuming and expensive part of UAV campaigns. Recently, deep learning has been rapidly developed in the field of small object detection. In this letter, to automatically extract coordinates information of ground control points (GCPs) by detecting GCP-markers in UAV images, we propose a solution that uses a deep learning-based architecture, YOLOv5-OBB, combined with a confidence threshold filtering…
LTV-YOLO: A Lightweight Thermal Object Detector for Young Pedestrians in Adverse Conditions
Automotive and Surface Transportation National Research Council Canada（交通运输国家研究院加拿大）；Department of Civil and Environmental Engineering University of Western Ontario（土木与环境工程系温哥华大学）
Although the YOLOv2 method is extremely fast on object detection, its detection accuracy is restricted due to the low performance of its backbone network and the underutilization of multi-scale region features. Therefore, a dense connection (DC) and spatial pyramid pooling (SPP) based YOLO (DC-SPP-YOLO) method for ameliorating the object detection accuracy of YOLOv2 is proposed in this paper. Specifically, the dense connection of convolution layers is employed in the backbone network of YOLOv2 to strengthen the feature extraction and alleviate the vanishing-gradient problem. Moreover, an impro…
Wave Processes and Control Systems Lab, MIPT（莫斯科物理技术学院波动过程与控制系统实验室）
We propose a method of improving detection precision (mAP) with the help of the prior knowledge about the scene geometry: we assume the scene to be a plane with objects placed on it. We focus our attention on autonomous robots, so given the robot's dimensions and the inclination angles of the camera, it is possible to predict the spatial scale for each pixel of the input frame. With slightly modified YOLOv3-tiny we demonstrate that the detection supplemented by the scale channel, further referred as S, outperforms standard RGB-based detection with small computational overhead.
School of Science and Engineering, Chuo University（中央大学理工学部）；RITECS Inc.（RITECS公司）
This paper aims at constructing a light-weight object detector that inputs a depth and a color image from a stereo camera. Specifically, by extending the network architecture of YOLOv3 to 3D in the middle, it is possible to output in the depth direction. In addition, Intersection over Uninon (IoU) in 3D space is introduced to confirm the accuracy of region extraction results. In the field of deep learning, object detectors that use distance information as input are actively studied for utilizing automated driving. However, the conventional detector has a large network structure, and the real-t…
University of Guelph（圭尔夫大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；Canadian Institute for Advanced Research（加拿大高级研究所）
Deep learning methods for computer vision tasks show promise for automating the data analysis of camera trap images. Ecological camera traps are a common approach for monitoring an ecosystem's animal population, as they provide continual insight into an environment without being intrusive. However, the analysis of camera trap images is expensive, labour intensive, and time consuming. Recent advances in the field of deep learning for object detection show promise towards automating the analysis of camera trap images. Here, we demonstrate their capabilities by training and comparing two deep lea…
Federal University of Paraná（巴拉那联邦大学）；Federal University of Minas Gerais（米纳斯吉拉斯联邦大学）
Automatic License Plate Recognition (ALPR) has been a frequent topic of research due to many practical applications. However, many of the current solutions are still not robust in real-world situations, commonly depending on many constraints. This paper presents a robust and efficient ALPR system based on the state-of-the-art YOLO object detector. The Convolutional Neural Networks (CNNs) are trained and fine-tuned for each ALPR stage so that they are robust under different conditions (e.g., variations in camera, lighting, and background). Specially for character segmentation and recognition, w…
The Hong Kong University of Science and Technology（香港科技大学）；Chinese Academy of Sciences（中国科学院）
Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs. Nowadays, most of the best-performing frameworks for stereo 3D object detection are based on dense depth reconstruction from disparity estimation, making them extremely computationally expensive. To enable real-world deployments of vision detection with binocular images, we take a step back to gain insights from 2D image-based detection frameworks and enhance them with stereo features. We incorporate knowledge and the inference …
MS-YOLO: Infrared Object Detection for Edge Deployment via MobileNetV4 and SlideLoss
Dept. of Mathematics & Statistics, Missouri University of Science and Technology（数学与统计学系，密苏里科学与技术大学）；Dept. of Computer Science, Missouri University of Science and Technology（计算机科学系，密苏里科学与技术大学）；School of Electrical & Computer Engineering, University of Oklahoma（电气与计算机工程学院，俄克拉荷马大学）；Kummer Institute Center for Artificial Intelligence and Autonomous Systems, Missouri University of Science and Technology（人工智能与自主系统中心，密苏里科学与技术大学）
This study examines the effectiveness of spatio-temporal modeling and the integration of spatial attention mechanisms in deep learning models for underwater object detection. Specifically, in the first phase, the performance of temporal-enhanced YOLOv5 variant T-YOLOv5 is evaluated, in comparison with the standard YOLOv5. For the second phase, an augmented version of T-YOLOv5 is developed, through the addition of a Convolutional Block Attention Module (CBAM). By examining the effectiveness of the already pre-existing YOLOv5 and T-YOLOv5 models and of the newly developed T-YOLOv5 with CBAM. Wit…
New York University（纽约大学）；NYU Tandon School of Engineering（纽约大学坦登工程学院）；New York University Abu Dhabi（纽约大学阿布扎比分校）；NYU Langone Health（纽约大学朗格尼医学中心）
Deep learning has made great strides for object detection in images. The detection accuracy and computational cost of object detection depend on the spatial resolution of an image, which may be constrained by both the camera and storage considerations. Compression is often achieved by reducing either spatial or amplitude resolution or, at times, both, both of which have well-known effects on performance. Detection accuracy also depends on the distance of the object of interest from the camera. Our work examines the impact of spatial and amplitude resolution, as well as object distance, on obje…
YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidification
Chongqing University of Posts and Telecommunications（重庆邮电大学）；Chongqing University（重庆大学）；Inspur Yunzhou Industrial Internet Co., Ltd（浪潮云洲工业互联网有限公司）；Guoqi Zhimo (Chongqing) Technology Co., Ltd（国汽智眸（重庆）科技有限公司）；Shenzhen University（深圳大学）
Determining the distance between the objects in a scene and the camera sensor from 2D images is feasible by estimating depth images using stereo cameras or 3D cameras. The outcome of depth estimation is relative distances that can be used to calculate absolute distances to be applicable in reality. However, distance estimation is very challenging using 2D monocular cameras. This paper presents a deep learning framework that consists of two deep networks for depth estimation and object detection using a single image. Firstly, objects in the scene are detected and localized using the You Only Lo…
University of Washington（华盛顿大学）；University of Tokyo（东京大学）；Microsoft Research（微软研究院）
Tracking of multiple objects is an important application in AI City geared towards solving salient problems related to safety and congestion in an urban environment. Frequent occlusion in traffic surveillance has been a major problem in this research field. In this challenge, we propose a model-based vehicle localization method, which builds a kernel at each patch of the 3D deformable vehicle model and associates them with constraints in 3D space. The proposed method utilizes shape fitness evaluation besides color information to track vehicle objects robustly and efficiently. To build 3D car m…
Interpretable Dynamic Graph Neural Networks for Small Occluded Object Detection and Tracking
Department of Computer Science, American International University-Bangladesh（美国国际大学-孟加拉国计算机科学系）；Department of Industrial Engineering and Management, Khulna University of Engineering and Technology (KUET)（Khulna工程与技术大学工业工程与管理系）；Physics and Biology Unit, Okinawa Institute of Science and Technology Graduate University (OIST)（冲绳科学与技术研究生大学物理与生物学单元）
Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm
University of Chicago（芝加哥大学）；University of Michigan（密歇根大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Shanghai Jiao Tong University（上海交通大学）；Tulane University（杜兰大学）；Northeastern University（东北大学）
Prince Sultan University（苏丹王子大学）；Polytechnic Institute of Porto（波尔图理工学院）；University of Carthage（迦太基大学）
In this paper, we address the problem of car detection from aerial images using Convolutional Neural Networks (CNN). This problem presents additional challenges as compared to car (or any object) detection from ground images because features of vehicles from aerial images are more difficult to discern. To investigate this issue, we assess the performance of two state-of-the-art CNN algorithms, namely Faster R-CNN, which is the most popular region-based algorithm, and YOLOv3, which is known to be the fastest detection algorithm. We analyze two datasets with different characteristics to check th…
Automated Defect Detection for Mass-Produced Electronic Components Based on YOLO Object Detection Models
Department of Electrical Engineering and Graduate School of Engineering Science and Technology（电气工程系和工程科学与技术研究生学院）；National Yunlin University of Science and Technology（云林科技大学）；Research Center for Information Technology Innovation（信息技术创新研究中心）；Academia Sinica（学术院）；Institute of Communications Engineering（通讯工程研究所）；National Sun Yat-sen University（国立中山大学）
An Improved YOLOv8 Approach for Small Target Detection of Rice Spikelet Flowering in Field Environments
Shenzhen Institute of Modern Agricultural Equipment（深圳现代农业装备研究院）；Guangdong Institute of Modern Agricultural Equipment（广东现代农业装备研究院）；Key Laboratory of Modern Agricultural Intelligent Equipment in South China, Ministry of Agriculture and Rural Affairs（南方现代农业智能装备重点实验室，农业部）；Agro-Tech Extension Center of Guangdong Province（广东省农业技术推广中心）
