Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine

Pedestrians are the vulnerable participants in transportation system when crashes happen. It is important to detect pedestrian efficiently and accurately in many computer vision applications, such as intelligent transportation systems (ITSs) and safety driving assistant systems (SDASs). This paper proposes a two-stage pedestrian detection method based on machine vision. In the first stage, AdaBoost algorithm and cascading method are adopted to segment pedestrian candidates from image. To confirm whether each candidate is pedestrian or not, a second stage is needed to eliminate some false positives. In this stage, a pedestrian recognizing classifier is trained with support vector machine (SVM). The input features used for SVM training are extracted from both the sample gray images and edge images. Finally, the performance of the proposed pedestrian detection method is tested with real-world data. Results show that the performance is better than conventional single-stage classifier, such as AdaBoost based or SVM based classifier.     

High-performance and deep pedestrian detection based on estimation of different parts

Pedestrian detection, despite the recent advances, still is of a great challenge to computer vision in wide range of diversified applications such as urban autonomous driving and intelligent transportation. Deep convolutional neural network has greatly contributed to the recent advances in pedestrian detection algorithms. The aim of this paper is to use modified single-shot detector (SSD) approach in pedestrian detection and then improve it by a novel deep architecture. The proposed deep architecture extracts initial Region of Interests (RoIs) using SSD approach, while it employs nine parallel fast RCNNs based on inception modules to estimate nine different parts of body. The proposed method takes the advantage of a secure border in each initial RoI to both create an Extended Region of Candidate Pedestrian (ERCP) and also to extract multi-RoIs. It then selects a number of RoIs within the ERCP as detected pedestrians which satisfy few reasonable criteria. We also propose a new training approach based on different body parts estimation which searches the best RoIs. Comprehensive experimental results demonstrate that the proposed method, deep model based on parts in pedestrian proposals, is a highly effective method that achieves very competitive performance on two most popular pedestrian detection datasets: Caltech-USA and INRIA. We have improved the log-average miss rate on the Caltech-USA and INRIA pedestrian datasets to 7.28% and 4.96%, respectively.

     

车辆辅助驾驶系统中基于计算机视觉的行人检测研究综述

基于计算机视觉的行人检测由于其在车辆辅助驾驶系统中的重要应用价值成为当前计算机视觉和智能车辆领域最为活跃的研究课题之一. 其核心是利用安装在运动车辆上的摄像机检测行人，从而估计出潜在的危险以便采取策略保护行人.本文在对这一问题存在的困难进行分析的基础上，对相关文献进行综述. 基于视觉的行人检测系统一般包括两个模块:感兴趣区分割和目标识别，本文介绍了这两个模块所采用的一些典型方法，分析了每种方法的原理和优缺点. 最后对性能评估和未来的研究方向等一系列关键问题给予了介绍.     

基于HOG特征的行人视觉检测方法

行人检测是近年来计算机视觉领域中备受关注的前沿方向和研究热点.以单目视觉传感器作为外界环境信息获取的主要手段,建立了一个包含行人分割、识别的检测系统.根据行人特有的一些特征,提出了基于垂直边缘和边缘对称性的行人分割方法,并进行精确定位.在行人识别阶段利用HOG特征进行特征提取,然后利用线性支持向量机进行行人识别.对大量...     

基于机器视觉的车道线检测研究进展综述

针对车道线检测技术在车道偏离预警、自动泊车和车道变换等各种辅助驾驶系统中的重要作用,国内外专家学者对车道线检测技术做了较多的研究,但是近年来少见有关于车道线检测的综述,因此本文主要阐述了近几年国内外机器视觉的车道线检测研究进展。首先简单介绍了机器视觉的车道线检测的基本流程;其次重点阐述了基于特征、基于模型和基于深度学习三种典型方法的基本检测原理和研究现状,并对比三种典型研究方法;最后,提出了机器视觉的车道线检测方法主要存在的问题,并针对问题提出未来的发展方向。     

Multi Criteria Decision Making System for Parking System

System supported smart parking can reduce traffic by making it stress free to locate empty parking spaces, hence lowering the risk of unfocussed driving. In this study, we propose a smart parking system using deep learning and an application-based approach. This system has two modules, one module detects and recognizes a license plate (LP), and the other selects a parking space; both modules use deep learning techniques. We used two modules that work independently to detect and recognize an LP by using an image of the vehicle. To detect parking space, only deep learning techniques were used. The two modules were compared with other state-of-the-art solutions. We utilized the You Only Look Once (YOLO) architecture to detect and recognize an LP because its performance in the context of Saudi Arabian LP numbers was superior to that of other solutions. Compared with existing state-of-the-art solutions, the performance of the proposed solution was more effective. The solution can be further improved for use in the city and large organizations that have priority parking spaces. A dataset of LP-annotated images of vehicles was used. The results of this study have considerable implications for smart parking, particularly in universities; in addition, they can be utilized for smart cities.     

基于车内外视觉信息的行人碰撞预警方法

行人碰撞预警系统通常依据行人检测与碰撞时间判断的方式为驾驶员提供预警信息。为了提供更加可靠的危险判断依据，本文提出一种同时分析道路状况与驾驶员头部姿态的行人碰撞预警方法，用两个单目相机分别获取车辆内外环境图像。通道特征检测器用于定位行人，根据单目视觉距离测量方法估计出行人与自车间的纵向与横向距离。多任务级联卷积网络用于定位驾驶员面部特征点，通过求解多点透视问题获取头部方向角以反映驾驶员注意状态。结合行人位置信息与驾驶员状态信息，本文构建模糊推理系统判断碰撞风险等级。在实际路况下的实验结果表明，根据模糊系统输出的风险等级可以为预防碰撞提供有效的指导。     

自动驾驶场景的尺度感知实时行人检测

目的 行人检测是目标检测中的一个基准问题,在自动驾驶等场景有着较大的实用价值,在路径规划和智能避障方面发挥着重要作用。受限于现实的算法功耗和运行效率,在自动驾驶场景下行人检测存在检测速度不佳、遮挡行人检测精度不足和小尺度行人漏检率高等问题,在保证实时性的前提下设计一种适合行人检测的算法,是一项挑战性的工作。方法 本文旨在解决自动驾驶场景中耗时长、行人遮挡和小尺度行人检测结果精度低的问题,提出了一种尺度注意力并行检测算法（scale-aware and efficient object detection,Scale-aware EfficientDet）：在特征提取与检测中使用了EfficientDet的主干网络,保证算法效率和功耗的平衡;在行人遮挡方面,为了提高模型对遮挡现象的检测精度,引入了可以增强行人与其他物体之间特征差异的损失函数;在提高小目标行人检测精度方面,采用scale-aware双路网络算法来增加对小目标行人的检测精度。结果 本文选择Caltech行人数据集作为对比数据集,选取YOLO（you only look once）、YOLOv3、SA-FastRCNN（scale-aware fast region-based convolutional neural network）等算法进行对比,在运行效率方面,本文算法在连续输入单帧图像的情况下达到了35帧/s,多图像输入时达到了70帧/s的工作效率;在模型精度测试中,本文算法也略胜一筹。本文算法应用于2020年中国智能汽车大赛中,在安全避障环节皆获得满分。结论 本文设计的尺度感知的行人检测算法,在EfficientDet高性能检测器的基础上,通过结合损失函数、scale-aware双路子网络的改进,进一步提升了本文检测器的鲁棒性。     

Modeling parallel parking a car

In the paper, first results of the work on the development of an automated control system for parallel parking a car are presented. Parallel parking a car is an example of a frequently performed maneuver with high cost of a mistake, which makes creation of control systems for automated parking very important. An analytical method for solving the problem and numerical simulation of the process of car parking presented in the paper are intermediate results of the work on the development of an adaptive control system for car parking. Examples of parallel parking a car for some particular cases of mutual location of obstacles and the desired slot in the parking place are presented.     

Tracking Pedestrians Under Occlusion in Parking Space

Many traffic accidents occur in parking lots. One of the serious safety risks is vehicle-pedestrian conflict. Moreover, with the increasing development of automatic driving and parking technology, parking safety has received significant attention from vehicle safety analysts. However, pedestrian protection in parking lots still faces many challenges. For example, the physical structure of a parking lot may be complex, and dead corners would occur when the vehicle density is high. These lead to pedestrians’ sudden appearance in the vehicle’s path from an unexpected position, resulting in collision accidents in the parking lot. We advocate that besides vehicular sensing data, high-precision digital map of the parking lot, pedestrians’ smart device’s sensing data, and attribute information of pedestrians can be used to detect the position of pedestrians in the parking lot. However, this subject has not been studied and explored in existing studies. To fill this void, this paper proposes a pedestrian tracking framework integrating multiple information sources to provide pedestrian position and status information for vehicles and protect pedestrians in parking spaces. We also evaluate the proposed method through real-world experiments. The experimental results show that the proposed framework has its advantage in pedestrian attribute information extraction and positioning accuracy. It can also be used for pedestrian tracking in parking spaces.     

An integrated driver warning system for driver and pedestrian safety

A semi-integrated system for driver assistance and pedestrian safety is presented. This system is composed of a single camera which focuses on the driver for picking up visual cues and a stereo rig that focus on the road ahead for the detection of road obstructions and pedestrians. While the car is in motion, the driver's viewing direction is obtained and analyzed along with information of road condition and any moving vehicle ahead in order to determine if the current driving condition is safe. In addition, when the vehicle is moving slowly, the system can also detect the existence of a pedestrian ahead and warns the driver if the pedestrian moves in front of the car. This system contains algorithm-based safety analysis as well as fuzzy rules-based analysis for interaction between variables. Our experimental results show that the condition for driver safety can be accurately classified in 94.5% of the tested driving conditions, and the pedestrians can be identified in 93.18% of the tested cases. These were compared to the results of similar systems and shown to be superior.     

A single-shot model for traffic-related pedestrian detection

Pattern Analysis and Applications - Traffic-related pedestrian detection is important for advanced driving-assistant systems and autonomous driving. In addition to pedestrian detection,...     

Computing with biological switches and clocks

The complex dynamics of biological systems is primarily driven by molecular interactions that underpin the regulatory networks of cells. These networks typically contain positive and negative feedback loops, which are responsible for switch-like and oscillatory dynamics, respectively. Many computing systems rely on switches and clocks as computational modules. While the combination of such modules in biological systems leads to a variety of dynamical behaviours, it is also driving development of new computing algorithms. Here we present a historical perspective on computation by biological systems, with a focus on switches and clocks, and discuss parallels between biology and computing. We also outline our vision for the future of biological computing.     

基于迁移学习的行人检测研究进展

行人检测是计算机视觉的研究热点和难点,近年来基于机器学习的行人检测技术取得了长足的进步,但由于不同场景的数据分布存在差异,已有检测器在新场景下的行人检测性能出现显著下降。为了避免繁琐的人工标注,充分利用原有检测器和标注样本,基于迁移学习的行人检测研究受到越来越多的关注。对其中涉及到的样本获取、迁移学习机制等关键技术进行综述,并从多个角度对现有方法进行分析和比较,最后对该技术的未来进行展望。     

Developing robust vision modules for microsystems applications

In this work, several robust vision modules are developed and implemented for fully automated micromanipulation. These are autofocusing, object and end-effector detection, real-time tracking and optical system calibration modules. An image based visual servoing architecture and a path planning algorithm are also proposed based on the developed vision modules. Experimental results are provided to assess the performance of the proposed visual servoing approach in positioning and trajectory tracking tasks. Proposed path planning algorithm in conjunction with visual servoing imply successful micromanipulation tasks.     

改进YOLOv3的车辆实时检测与信息识别技术

在复杂无约束自然场景下对车辆实时检测和相关信息的提取识别一直是计算机视觉领域内重要的研究内容之一。该领域问题的突破不但可以为汽车自动驾驶技术的实现和完善带来实际效果的提升,并且在停车场的自动停车调度算法和实时泊车监控系统的改进上有着重要的现实意义。针对当前实时车辆信息检测中存在的车辆检测区域不完整、精度不高以及无法对场景中较远车辆进行准确定位等相关问题,提出了一种Vehicle-YOLO的实时车辆检测分类模型。该模型在最新的YOLOv3算法基础上,通过更改图像输入参数,增强深度残差网络的特征提取能力,采用5个不同尺寸的特征图依次对潜在车辆的边界框提取等方式来提升车辆实时信息检测的精度和普适性,并通过KITTI、VOC等数据集进行性能验证和分析。实验结果表明,Vehicle-YOLO模型在KITTI数据集上达到了96%的均值平均精度,传输速度约为40 f/s,在精度提升的情况下仍能保持良好的实时检测速率。此外,Vehicle-YOLO检测模型在VOC等其余数据集上的实验结果也展现了不同程度的精度提升,故该模型在常见物体的定位检测中有较好的普适性,相较于传统的物体检测算法模型有更好的表现。     

An Advanced Parking Navigation System for Downtown Parking

This paper develops a novel parking navigation system for downtown parking that aims to mitigate parking competition by guiding drivers to appropriate vacant parking spaces. Given drivers’ real-time locations and their parking preferences, a two-sided matching algorithm is firstly adopted to achieve a stable driver-optimal matching, under which drivers will be assigned to their most appropriate parking spaces (if any), and have no incentive to misreport their private information (e.g., parking space preferences). Although drivers’ private information is required for the navigation system, a distributed solution procedure is applied to achieve the space assignment without disclosing such information. Lastly, simulation experiments are conducted to demonstrate the capability of the proposed navigation system on reducing driving time and the frequency of changed navigation compared with other navigation systems.

     

3D visual perception for self-driving cars using a multi-camera system: Calibration,mapping, localization,and obstacle detection

Cameras are a crucial exteroceptive sensor for self-driving cars as they are low-cost and small, provide appearance information about the environment, and work in various weather conditions. They can be used for multiple purposes such as visual navigation and obstacle detection. We can use a surround multi-camera system to cover the full 360-degree field-of-view around the car. In this way, we avoid blind spots which can otherwise lead to accidents. To minimize the number of cameras needed for surround perception, we utilize fisheye cameras. Consequently, standard vision pipelines for 3D mapping, visual localization, obstacle detection, etc. need to be adapted to take full advantage of the availability of multiple cameras rather than treat each camera individually. In addition, processing of fisheye images has to be supported. In this paper, we describe the camera calibration and subsequent processing pipeline for multi-fisheye-camera systems developed as part of the V-Charge project. This project seeks to enable automated valet parking for self-driving cars. Our pipeline is able to precisely calibrate multi-camera systems, build sparse 3D maps for visual navigation, visually localize the car with respect to these maps, generate accurate dense maps, as well as detect obstacles based on real-time depth map extraction.     

Pedestrian detection and tracking at crossroads

This paper presents a system that can perform pedestrian detection and tracking using vision-based techniques. A very important issue in the field of intelligent transportation system is to prevent pedestrians from being hit by vehicles. Recently, a great number of vision-based techniques have been proposed for this purpose. In this paper, we propose a vision-based method, which combines the use of a pedestrian model as well as the walking rhythm of pedestrians to detect and track walking pedestrians. Through integrating some spatial and temporal information grabbed by a vision system, we are able to develop a reliable system that can be used to prevent traffic accidents happened at crossroads. In addition, the proposed system can deal with the occlusion problem. Experimental results obtained by executing some real world cases have demonstrated that the proposed system is indeed superb.     

Nonlinear model-based track guidance of user-defined points at the vehicle front

Preventive pedestrian protection systems are validated by means of fully automated driving tests reproducing safety-critical traffic situations on a proving ground. In order to assess these preventive safety systems, a precise and reproducible collision of a pedestrian dummy with a specific point at the vehicle front, e.g., the left corner of the vehicle, must be ensured. Hence, a track guidance of this specific point is required. Beyond the state of the art a new nonlinear model describing the lateral deviation of any point at the vehicle front to a predefined path is proposed in this paper. Based on this model the method of input–output linearization is used to design a flexible lateral guidance system for an easy application in different vehicles. Furthermore, the closed-loop stability is proven and experimental results are presented.