The rapid development of embedded hardware in autonomous vehicles broadens their computational capabilities, thus bringing the possibility to mount more complete sensor setups able to handle driving scenarios of higher complexity. As a result, new challenges such as multiple detections of the same object have to be addressed. In this work, a siamese network is integrated into the pipeline of a well-known 3D object detector approach to suppress duplicate proposals coming from different cameras via re-identification. Additionally, associations are exploited to enhance the 3D box regression of the object by aggregating their corresponding LiDAR frustums. The experimental evaluation on the nuScenes dataset shows that the proposed method outperforms traditional NMS approaches.
In monocular 3D human pose estimation a common setup is to first detect 2D positions and then lift the detection into 3D coordinates. Many algorithms suffer from overfitting to camera positions in the training set. We propose a siamese architecture that learns a rotation equivariant hidden representation to reduce the need for data augmentation. Our method is evaluated on multiple databases with different base networks and shows a consistent improvement of error metrics. It achieves state-of-the-art cross-camera error rate among algorithms that use estimated 2D joint coordinates only.
South China University of Technology（华南理工大学）；Central South University（中南大学）；Peking University（北京大学）；Southwest Jiaotong University（西南交通大学）
A critical challenge problem of scene change detection is that noisy changes generated by varying illumination, shadows and camera viewpoint make variances of a scene difficult to define and measure since the noisy changes and semantic ones are entangled. Following the intuitive idea of detecting changes by directly comparing dissimilarities between a pair of features, we propose a novel fully Convolutional siamese metric Network(CosimNet) to measure changes by customizing implicit metrics. To learn more discriminative metrics, we utilize contrastive loss to reduce the distance between the unc…
University of Kansas（堪萨斯大学）；Ryerson University（瑞尔森大学）
The paper proposes a light-weighted stereo frustums matching module for 3D objection detection. The proposed framework takes advantage of a high-performance 2D detector and a point cloud segmentation network to regress 3D bounding boxes for autonomous driving vehicles. Instead of performing traditional stereo matching to compute disparities, the module directly takes the 2D proposals from both the left and the right views as input. Based on the epipolar constraints recovered from the well-calibrated stereo cameras, we propose four matching algorithms to search for the best match for each propo…
CoreNet: Conflict Resolution Network for Point-Pixel Misalignment and Sub-Task Suppression of 3D LiDAR-Camera Object Detection
State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation（多模态人工智能系统国家重点实验室（MAIS）自动化研究所）；School of Artificial Intelligence（人工智能学院）
Federal University of Technology - Paran\' a (UTFPR), Curitiba, Brazil
We describe in this paper a Two-Stream Siamese Neural Network for vehicle re-identification. The proposed network is fed simultaneously with small coarse patches of the vehicle shape's, with 96 x 96 pixels, in one stream, and fine features extracted from license plate patches, easily readable by humans, with 96 x 48 pixels, in the other one. Then, we combined the strengths of both streams by merging the Siamese distance descriptors with a sequence of fully connected layers, as an attempt to tackle a major problem in the field, false alarms caused by a huge number of car design and models with …
6DOF camera relocalization is an important component of autonomous driving and navigation. Deep learning has recently emerged as a promising technique to tackle this problem. In this paper, we present a novel relative geometry-aware Siamese neural network to enhance the performance of deep learning-based methods through explicitly exploiting the relative geometry constraints between images. We perform multi-task learning and predict the absolute and relative poses simultaneously. We regularize the shared-weight twin networks in both the pose and feature domains to ensure that the estimated pos…
Domain gaps of sensor modalities pose a challenge for the design of autonomous robots. Taking a step towards closing this gap, we propose two unsupervised training frameworks for finding a common representation of LiDAR and camera data. The first method utilizes a double Siamese training structure to ensure consistency in the results. The second method uses a Canny edge image guiding the networks towards a desired representation. All networks are trained in an unsupervised manner, leaving room for scalability. The results are evaluated using common computer vision applications, and the limitat…
Hyperspectral anomalous change detection has been a challenging task for its emphasis on the dynamics of small and rare objects against the prevalent changes. In this paper, we have proposed a Multi-Temporal spatial-spectral Comparison Network for hyperspectral anomalous change detection (MTC-NET). The whole model is a deep siamese network, aiming at learning the prevalent spectral difference resulting from the complex imaging conditions from the hyperspectral images by contrastive learning. A three-dimensional spatial spectral attention module is designed to effectively extract the spatial se…
National Institute of Advanced Industrial Science and Technology（产业技术综合研究所）；Artificial Intelligence Research Center（人工智能研究中心）
This paper presents a novel semantic scene change detection scheme with only weak supervision. A straightforward approach for this task is to train a semantic change detection network directly from a large-scale dataset in an end-to-end manner. However, a specific dataset for this task, which is usually labor-intensive and time-consuming, becomes indispensable. To avoid this problem, we propose to train this kind of network from existing datasets by dividing this task into change detection and semantic extraction. On the other hand, the difference in camera viewpoints, for example, images of t…
There have been significant advances in neural networks for both 3D object detection using LiDAR and 2D object detection using video. However, it has been surprisingly difficult to train networks to effectively use both modalities in a way that demonstrates gain over single-modality networks. In this paper, we propose a novel Camera-LiDAR Object Candidates (CLOCs) fusion network. CLOCs fusion provides a low-complexity multi-modal fusion framework that significantly improves the performance of single-modality detectors. CLOCs operates on the combined output candidates before Non-Maximum Suppres…
Cambricon Technologies（寒武纪科技）；University of Chinese Academy of Sciences（中国科学院大学）
Domain adaptation methods face performance degradation in object detection, as the complexity of tasks require more about the transferability of the model. We propose a new perspective on how CNN models gain the transferability, viewing the weights of a model as a series of motion patterns. The directions of weights, and the gradients, can be divided into domain-specific and domain-invariant parts, and the goal of domain adaptation is to concentrate on the domain-invariant direction while eliminating the disturbance from domain-specific one. Current UDA object detection methods view the two di…
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 …
In this paper, we present a novel dataset named MVB (Multi View Baggage) for baggage ReID task which has some essential differences from person ReID. The features of MVB are three-fold. First, MVB is the first publicly released large-scale dataset that contains 4519 baggage identities and 22660 annotated baggage images as well as its surface material labels. Second, all baggage images are captured by specially-designed multi-view camera system to handle pose variation and occlusion, in order to obtain the 3D information of baggage surface as complete as possible. Third, MVB has remarkable inte…
University of Science and Technology of China（中国科学技术大学）；Michigan State University（密歇根州立大学）
Camera trace is a unique noise produced in digital imaging process. Most existing forensic methods analyze camera trace to identify image origins. In this paper, we address a new low-level vision problem, camera trace erasing, to reveal the weakness of trace-based forensic methods. A comprehensive investigation on existing anti-forensic methods reveals that it is non-trivial to effectively erase camera trace while avoiding the destruction of content signal. To reconcile these two demands, we propose Siamese Trace Erasing (SiamTE), in which a novel hybrid loss is designed on the basis of Siames…
In this paper, we study the challenging problem of multi-object tracking in a complex scene captured by a single camera. Different from the existing tracklet association-based tracking methods, we propose a novel and efficient way to obtain discriminative appearance-based tracklet affinity models. Our proposed method jointly learns the convolutional neural networks (CNNs) and temporally constrained metrics. In our method, a Siamese convolutional neural network (CNN) is first pre-trained on the auxiliary data. Then the Siamese CNN and temporally constrained metrics are jointly learned online to…
Matching pedestrians across multiple camera views, known as human re-identification, is a challenging research problem that has numerous applications in visual surveillance. With the resurgence of Convolutional Neural Networks (CNNs), several end-to-end deep Siamese CNN architectures have been proposed for human re-identification with the objective of projecting the images of similar pairs (i.e. same identity) to be closer to each other and those of dissimilar pairs to be distant from each other. However, current networks extract fixed representations for each image regardless of other images …
Event cameras are novel sensors that perceive the per-pixel intensity changes and output asynchronous event streams, showing lots of advantages over traditional cameras, such as high dynamic range (HDR) and no motion blur. It has been shown that events alone can be used for object tracking by motion compensation or prediction. However, existing methods assume that the target always moves and is the stand-alone object. Moreover, they fail to track the stopped non-independent moving objects on fixed scenes. In this paper, we propose a novel event-based object tracking framework, called SiamEvent…
Vicomtech Foundation（Vicomtech基金会）；Public University of Navarre（纳瓦拉公立大学）；Netherlands Forensic Institute（荷兰法医学研究所）
Biometric systems represent valid solutions in tasks like user authentication and verification, since they are able to analyze physical and behavioural features with high precision. However, especially when physical biometrics are used, as is the case of iris recognition, they require specific hardware such as retina scanners, sensors, or HD cameras to achieve relevant results. At the same time, they require the users to be very close to the camera to extract high-resolution information. For this reason, in this work, we propose a novel approach that uses long-range (LR) distance images for im…
Deep Learning methods have been extensively used to analyze video data to extract valuable information by classifying image frames and detecting objects. We describe a unique approach for using video feed from a moving Locomotive to continuously monitor the Railway Track and detect significant assets like Switches on the Track. The technique used here is called Siamese Networks, which uses 2 identical networks to learn the similarity between of 2 images. Here we will use a Siamese network to continuously compare Track images and detect any significant difference in the Track. Switch will be on…
The University of Queensland（昆士兰大学）；Dalian University of Technology（大连理工大学）；The University of Sydney（悉尼大学）
Video-based person re-identification (re-id) is a central application in surveillance systems with significant concern in security. Matching persons across disjoint camera views in their video fragments is inherently challenging due to the large visual variations and uncontrolled frame rates. There are two steps crucial to person re-id, namely discriminative feature learning and metric learning. However, existing approaches consider the two steps independently, and they do not make full use of the temporal and spatial information in videos. In this paper, we propose a Siamese attention archite…
University of Washington（华盛顿大学）；Silkwave Holdings Limited（Silkwave控股有限公司）
Radar is usually more robust than the camera in severe driving scenarios, e.g., weak/strong lighting and bad weather. However, unlike RGB images captured by a camera, the semantic information from the radar signals is noticeably difficult to extract. In this paper, we propose a deep radar object detection network (RODNet), to effectively detect objects purely from the carefully processed radar frequency data in the format of range-azimuth frequency heatmaps (RAMaps). Three different 3D autoencoder based architectures are introduced to predict object confidence distribution from each snippet of…
The device used in this work detects the objects over the surface of the water using two thermal cameras which aid the users to detect and avoid the objects in scenarios where the human eyes cannot (night, fog, etc.). To avoid the obstacle collision autonomously, it is required to track the objects in real-time and assign a specific identity to each object to determine its dynamics (trajectory, velocity, etc.) for making estimated collision predictions. In the following work, a Machine Learning (ML) approach for Computer Vision (CV) called Convolutional Neural Network (CNN) was used using Tens…
Nanjing University of Posts and Telecommunications（南京邮电大学）；Nanjing University of Science and Technology（南京理工大学）
Robust road detection is a key challenge in safe autonomous driving. Recently, with the rapid development of 3D sensors, more and more researchers are trying to fuse information across different sensors to improve the performance of road detection. Although many successful works have been achieved in this field, methods for data fusion under deep learning framework is still an open problem. In this paper, we propose a Siamese deep neural network based on FCN-8s to detect road region. Our method uses data collected from a monocular color camera and a Velodyne-64 LiDAR sensor. We project the LiD…
PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection
School of Remote Sensing and Information Engineering, Wuhan University（武汉大学遥感与信息工程学院）；School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology（南京信息工程大学遥感与地理信息工程学院）；Guangxi Water & Power Design Institute CO., Ltd.（广西水电设计院有限公司）
Massachusetts Institute of Technology（麻省理工学院）；Toyota Research Institute（丰田研究所）；Carnegie Mellon University（卡内基梅隆大学）；Li Auto（理想汽车）；Tsinghua University（清华大学）
We introduce a framework for multi-camera 3D object detection. In contrast to existing works, which estimate 3D bounding boxes directly from monocular images or use depth prediction networks to generate input for 3D object detection from 2D information, our method manipulates predictions directly in 3D space. Our architecture extracts 2D features from multiple camera images and then uses a sparse set of 3D object queries to index into these 2D features, linking 3D positions to multi-view images using camera transformation matrices. Finally, our model makes a bounding box prediction per object …
Introducing Depth into Transformer-based 3D Object Detection
The Hong Kong University of Science and Technology（香港科技大学）；South China University of Technology（华南理工大学）；International Digital Economy Academy (IDEA)（国际数字经济研究院（IDEA））；Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）
本文提出深度感知 Transformer 框架 DAT，通过 DA-SCA 注入深度信息并以 DNS 损失抑制深度方向重复预测，显著提升多种相机 3D 检测器性能。
German Aerospace Center（德国航空航天中心）；Technical University of Munich（慕尼黑工业大学）
Automatic multi-class object detection in remote sensing images in unconstrained scenarios is of high interest for several applications including traffic monitoring and disaster management. The huge variation in object scale, orientation, category, and complex backgrounds, as well as the different camera sensors pose great challenges for current algorithms. In this work, we propose a new method consisting of a novel joint image cascade and feature pyramid network with multi-size convolution kernels to extract multi-scale strong and weak semantic features. These features are fed into rotation-b…
Following the Flow: Advection-Consistent Modeling for Event-based Small Object Detection
School of Information and Electronic Engineering, Shandong Technology and Business University（山东工商学院信息与电子工程学院）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Technische Universität Berlin（柏林工业大学）；Einstein Center Digital Future（爱因斯坦数字未来中心）；SCIoI Excellence Cluster（SCIoI卓越集群）
This work introduces a co-capture system for multi-animal visual data acquisition using conventional cameras and event cameras. Event cameras offer multiple advantages over frame-based cameras, such as a high temporal resolution and temporal redundancy suppression, which enable us to efficiently capture the fast and erratic movements of fish. We furthermore present an event-based multi-animal tracking algorithm, which proves the feasibility of the approach and sets the baseline for further exploration of combining the advantages of event cameras and conventional cameras for multi-animal tracki…
Sorbonne Universités（索邦大学）；University of Pittsburgh（匹兹堡大学）；Carnegie Mellon University（卡内基梅隆大学）
This paper introduces a framework of gesture recognition operating on the output of an event based camera using the computational resources of a mobile phone. We will introduce a new development around the concept of time-surfaces modified and adapted to run on the limited computational resources of a mobile platform. We also introduce a new method to remove dynamically backgrounds that makes full use of the high temporal resolution of event-based cameras. We assess the performances of the framework by operating on several dynamic scenarios in uncontrolled lighting conditions indoors and outdo…
Surveillance cameras are widely applied for indoor occupancy measurement and human movement perception, which benefit for building energy management and social security. To address the challenges of limited view angle of single camera as well as lacking of inter-camera collaboration, this study presents a non-overlapping multi-camera system to enlarge the surveillance area and devotes to retrieve the same person appeared from different camera views. The system is deployed in an office building and four-day videos are collected. By training a deep convolutional neural network, the proposed syst…
KAIST（韩国科学技术院）；Institute for Basic Science（基础科学研究院）
Relative camera pose estimation, i.e. estimating the translation and rotation vectors using a pair of images taken in different locations, is an important part of systems in augmented reality and robotics. In this paper, we present an end-to-end relative camera pose estimation network using a siamese architecture that is independent of camera parameters. The network is trained using the Cambridge Landmarks data with four individual scene datasets and a dataset combining the four scenes. To improve generalization, we propose a novel two-stage training that alleviates the need of a hyperparamete…
University of Science and Technology of China（中国科学技术大学）；City University of Hong Kong（香港城市大学）
The non-maximum suppression (NMS) is widely used in frame-based tasks as an essential post-processing algorithm. However, event-based NMS either has high computational complexity or leads to frequent discontinuities. As a result, the performance of event-based corner detectors is limited. This paper proposes a general-purpose asynchronous non-maximum suppression pipeline (ANMS), and applies it to corner event detection. The proposed pipeline extract fine feature stream from the output of original detectors and adapts to the speed of motion. The ANMS runs directly on the asynchronous event stre…
Dalian University of Technology（大连理工大学）；HiSilicon (Shanghai) Technologies Company Ltd.（海思（上海）科技有限公司）；Fuzhou University（福州大学）；Beijing University of Technology（北京工业大学）
University of Michigan（密歇根大学）；Nvidia Corporation（英伟达公司）
This paper proposes a new image-based localization framework that explicitly localizes the camera/robot by fusing Convolutional Neural Network (CNN) and sequential images' geometric constraints. The camera is localized using a single or few observed images and training images with 6-degree-of-freedom pose labels. A Siamese network structure is adopted to train an image descriptor network, and the visually similar candidate image in the training set is retrieved to localize the testing image geometrically. Meanwhile, a probabilistic motion model predicts the pose based on a constant velocity as…
Robotic apple harvesting has received much research attention in the past few years due to growing shortage and rising cost in labor. One key enabling technology towards automated harvesting is accurate and robust apple detection, which poses great challenges as a result of the complex orchard environment that involves varying lighting conditions and foliage/branch occlusions. This letter reports on the development of a novel deep learning-based apple detection framework named DeepApple. Specifically, we first collect a comprehensive apple orchard dataset for 'Gala' and 'Blondee' apples, using…
Existing pixel-level adversarial attacks on neural networks may be deficient in real scenarios, since pixel-level changes on the data cannot be fully delivered to the neural network after camera capture and multiple image preprocessing steps. In contrast, in this paper, we argue from another perspective that gaussian blurring, a common technique of image preprocessing, can be aggressive itself in specific occasions, thus exposing the network to real-world adversarial attacks. We first propose an adversarial attack demo named peak suppression (PS) by suppressing the values of peak elements in t…
AdvSerial: Physical Adversarial Attacks on Infrastructure-mounted Pedestrian Detectors via Semantic Feature Suppression
School of Transportation Science and Engineering, Beihang University（北京航空航天大学交通科学与工程学院）；State Key Lab of Intelligent Transportation System（智能交通系统国家重点实验室）；Zhongguancun Laboratory（中关村实验室）
Carnegie Mellon University（卡内基梅隆大学）；Fudan University（复旦大学）；Massachusetts Institute of Technology（麻省理工学院）；Li Auto（理想汽车）；Tsinghua University（清华大学）
Accurate and consistent 3D tracking from multiple cameras is a key component in a vision-based autonomous driving system. It involves modeling 3D dynamic objects in complex scenes across multiple cameras. This problem is inherently challenging due to depth estimation, visual occlusions, appearance ambiguity, etc. Moreover, objects are not consistently associated across time and cameras. To address that, we propose an end-to-end \textbf{MU}lti-camera \textbf{TR}acking framework called MUTR3D. In contrast to prior works, MUTR3D does not explicitly rely on the spatial and appearance similarity of…
A Robust Deep Networks based Multi-Object MultiCamera Tracking System for City Scale Traffic
COMSATS University Islamabad, Lahore Campus（COMSATS大学伊斯兰堡分校拉合尔校区）；Pakistan Navy Engineering College, National University of Sciences and Technology (NUST)（巴基斯坦国立科技大学巴基斯坦海军工程学院）
提出一种基于深度学习的多目标多摄像头跟踪框架，利用Mask R-CNN、迁移学习与Deep SORT等技术解决城市规模交通中的车辆跟踪难题，在AI City Challenge数据集上取得IDF1为0.8289的优异性能。
Huazhong University of Science and Technology（华中科技大学）
Aiming to improve the checkerboard corner detection robustness against the images with poor quality, such as lens distortion, extreme poses, and noise, we propose a novel detection algorithm which can maintain high accuracy on inputs under multiply scenarios without any prior knowledge of the checkerboard pattern. This whole algorithm includes a checkerboard corner detection network and some post-processing techniques. The network model is a fully convolutional network with improvements of loss function and learning rate, which can deal with the images of arbitrary size and produce correspondi…
calibfusion: Transformer-Based Differentiable Calibration for Radar-Camera Fusion Detection in Water-Surface Environments
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
[-15pt]1 Federal University of Technology - Paran\' a , Curitiba, Brazil 2 Federal University of Paran\'a, Curitiba, Brazil [0.5ex]
This work addresses the problem of vehicle identification through non-overlapping cameras. As our main contribution, we introduce a novel dataset for vehicle identification, called Vehicle-Rear, that contains more than three hours of high-resolution videos, with accurate information about the make, model, color and year of nearly 3,000 vehicles, in addition to the position and identification of their license plates. To explore our dataset we design a two-stream CNN that simultaneously uses two of the most distinctive and persistent features available: the vehicle's appearance and its license p…
In this technical report, we introduce our winning solution "HorizonLiDAR3D" for the 3D detection track and the domain adaptation track in Waymo Open Dataset Challenge at CVPR 2020. Many existing 3D object detectors include prior-based anchor box design to account for different scales and aspect ratios and classes of objects, which limits its capability of generalization to a different dataset or domain and requires post-processing (e.g. Non-Maximum Suppression (NMS)). We proposed a one-stage, anchor-free and NMS-free 3D point cloud object detector AFDet, using object key-points to encode the …
