Moving Obstacle Detection Research Articles

Dynamic obstacle detection method based on U–V disparity and residual optical flow for autonomous driving

As a core step of obstacle avoidance and path planning, dynamic obstacle detection is critical for autonomous driving. This study aimed to propose a dynamic obstacle detection method based on U–V disparity and residual optical flow for autonomous driving. First, a drivable area of an unmanned vehicle was detected using U–V disparity images. Then, obstacles in the drivable area were detected using U–V disparity images and the geometric relationship between obstacle size and its disparity. Finally, the motion likelihood of each obstacle was estimated by compensating the camera ego-motion. The innovation of the proposed method was that the searching range of the moving obstacles was greatly narrowed by detecting the obstacles in the drivable area, which greatly improved not only the moving obstacle detection efficiency but also the detection accuracy. Datasets from the KITTI benchmark and our self-acquired campus scene data were chosen as testing samples. The experimental results showed that our method could achieve high detection precision, low missed detection rate and less time consumption.

Performance evaluation of low-resolution monocular vision-based velocity estimation technique for moving obstacle detection and tracking

Performance evaluation of low-resolution monocular vision-based velocity estimation technique for moving obstacle detection and tracking

Performance evaluation of low-resolution monocular vision-based velocity estimation technique for moving obstacle detection and tracking

Performance evaluation of low-resolution monocular vision-based velocity estimation technique for moving obstacle detection and tracking

АЛГОРИТМ КОМПЛЕКСИРОВАНИЯ НЕСКОЛЬКИХ ИСТОЧНИКОВ ДАННЫХ В ОБЩУЮ КАРТУ ЗАНЯТОСТИ

The paper deals with the problem of constructing a passability model of environment witha large number of dynamic objects based on data from several different sensors. The aim of thework is to improve the algorithm for constructing the occupancy map by adding data from bothexisting algorithms for moving obstacles detection and from millimeter-wave automotive radar.The study solves the problem of combining data on static environment and dynamic objects intoone general passability model for further trajectory planning. The modification of the algorithmpresented in the article is able to combine data from both occupancy maps based on a threedimensional point cloud from any sensor such as lidar or radar, and arrays of bounding boxes ofobjects with known coordinates, sizes, and orientation. Data aggregation occurs at the level ofbuilding occupancy maps and does not impose requirements on the source of information aboutdynamic obstacles. The algorithm is able to refine the data on the position and size of the dynamicobject by speed from the radar, which allows to plan the trajectory taking into account the movementof dynamic objects. The parallel use of the classical approach allows to detect obstacles inthe event of an error in the output of the dynamic obstacle detection algorithm. The developedalgorithm works in real time on the Jetson AGX Xavier module, and is tested in real conditions ona mobile robotic platform in autonomous mode. Promising directions for further research to improvethe presented approach are formulated.

SaccadeFork: A lightweight multi-sensor fusion-based target detector

Commercialization of self-driving applications requires precision and reliability of the perception system due to the highly dynamic and complex road environment. Early perception systems either rely on the camera or on LiDAR for moving obstacle detection. With the development of vehicular sensors and deep learning technologies, the multi-view and sensor fusion based convolutional neural network (CNN) model for detection tasks has become a popular research area. In this paper, we present a novel multi-sensor fusion-based CNN model–SaccadeFork–that integrates the image and upsampled LiDAR point clouds as the input. SaccadeFork includes two modules: (1) a lightweight backbone that consists of hourglass convolution feature extraction module and a parallel dilation convolution module for adaptation of the system to different target sizes; (2) an anchor-based detection head. The model also considers deployment of resource-limited edge devices in the vehicle. Two refinement strategies, i.e., Mixup and Swish activation function are also adopted to improve the model. Comparison with a series of latest models on public dataset of KITTI shows that SaccadeFork can achieve the optimal detection accuracy on vehicles and pedestrians under different scenarios. The final model is also deployed and tested on a local dataset collected based on edge devices and low-cost sensor solutions, and the results show that the model can achieve real-time efficiency and high detection accuracy.

Human-Robot Perception in Industrial Environments: A Survey.

Perception capability assumes significant importance for human–robot interaction. The forthcoming industrial environments will require a high level of automation to be flexible and adaptive enough to comply with the increasingly faster and low-cost market demands. Autonomous and collaborative robots able to adapt to varying and dynamic conditions of the environment, including the presence of human beings, will have an ever-greater role in this context. However, if the robot is not aware of the human position and intention, a shared workspace between robots and humans may decrease productivity and lead to human safety issues. This paper presents a survey on sensory equipment useful for human detection and action recognition in industrial environments. An overview of different sensors and perception techniques is presented. Various types of robotic systems commonly used in industry, such as fixed-base manipulators, collaborative robots, mobile robots and mobile manipulators, are considered, analyzing the most useful sensors and methods to perceive and react to the presence of human operators in industrial cooperative and collaborative applications. The paper also introduces two proofs of concept, developed by the authors for future collaborative robotic applications that benefit from enhanced capabilities of human perception and interaction. The first one concerns fixed-base collaborative robots, and proposes a solution for human safety in tasks requiring human collision avoidance or moving obstacles detection. The second one proposes a collaborative behavior implementable upon autonomous mobile robots, pursuing assigned tasks within an industrial space shared with human operators.

Vision-Based Moving Obstacle Detection and Tracking in Paddy Field Using Improved Yolov3 and Deep SORT.

Using intelligent agricultural machines in paddy fields has received great attention. An obstacle avoidance system is required with the development of agricultural machines. In order to make the machines more intelligent, detecting and tracking obstacles, especially the moving obstacles in paddy fields, is the basis of obstacle avoidance. To achieve this goal, a red, green and blue (RGB) camera and a computer were used to build a machine vision system, mounted on a transplanter. A method that combined the improved You Only Look Once version 3 (Yolov3) and deep Simple Online and Realtime Tracking (deep SORT) was used to detect and track typical moving obstacles, and figure out the center point positions of the obstacles in paddy fields. The improved Yolov3 has 23 residual blocks and upsamples only once, and has new loss calculation functions. Results showed that the improved Yolov3 obtained mean intersection over union (mIoU) score of 0.779 and was 27.3% faster in processing speed than standard Yolov3 on a self-created test dataset of moving obstacles (human and water buffalo) in paddy fields. An acceptable performance for detecting and tracking could be obtained in a real paddy field test with an average processing speed of 5–7 frames per second (FPS), which satisfies actual work demands. In future research, the proposed system could support the intelligent agriculture machines more flexible in autonomous navigation.

Moving obstacles detection based on laser range finder measurements

The objective of this article is to propose data processing from laser range finder that will provide simple, fast, and reliable object recognition including moving objects. The whole method is based on four steps: segmentation, simplification, correspondence between consequent measurements, and object classification. Segmentation uses raw data from laser range finder and it is significant in logical connection of related segments. The most important step is simplification which provides data reduction and acceleration of object classification. The output of simplification is an object represented by significant points. Correspondence between consequent measurements is based on kd-tree nearest neighborhood search. The object is then classified by its spatial changes. These changes are evaluated by position of correspondent significant points. Input of proposed procedure is a probabilistic model of laser range finder. In this article, versatile probabilistic model of Hokuyo URM-30 LX was used. The method was verified by simulations and by tests in real environment. The results show that proposed method is reliable and with small modifications (of parameters), it is usable with any other planar laser range finder.

A real-time collision-free path planning of a rust removal robot using an improved neural network

In this paper, a real-time collision-free path planning of the rust removal robot in a ship environment is proposed, which is based on an improved biologically inspired neural network algorithm. This improved algorithm is based on the biologically inspired neural network and modified with obstacle detection sensors and kinematic state templates, and is implemented in a ship rust removal robot planning system for dynamic trajectory generation. The real-time optimal trajectory is generated by the biologically inspired neural network, and the moving obstacle detection process of a ship robot working on the wall is simulated with the obstacle detection sensors models. The local real-time trajectory can be re-planned by the updated local map information, where the obstacle detection sensors are used to inspect partial environment information and update the robot nearby information in real time in the original neural network algorithm. At the same time, the method of the kinematic state templates matching and searching is used to solve the pipes’ influence of the rust removal robot climbing on the wall, which can not only provide a smooth path, but also can judge the motion direction and turning angle of the robot. Comparison of the proposed approach with the simulation shows that the improved algorithm is capable of planning a real-time collision-free path with achieving the local environmental information and judging the rust removal robot’s motion direction and turning angle. This proposed algorithm can be good used in the ship rust removal robot.

3D Lidar-based static and moving obstacle detection in driving environments: An approach based on voxels and multi-region ground planes

Artificial perception, in the context of autonomous driving, is the process by which an intelligent system translates sensory data into an effective model of the environment surrounding a vehicle. In this paper, and considering data from a 3D-LIDAR mounted onboard an intelligent vehicle, a 3D perception system based on voxels and planes is proposed for ground modeling and obstacle detection in urban environments. The system, which incorporates time-dependent data, is composed of two main modules: (i) an effective ground surface estimation using a piecewise plane fitting algorithm and RANSAC-method, and (ii) a voxel-grid model for static and moving obstacles detection using discriminative analysis and ego-motion information. This perception system has direct application in safety systems for intelligent vehicles, particularly in collision avoidance and vulnerable road users detection, namely pedestrians and cyclists. Experiments, using point-cloud data from a Velodyne LIDAR and localization data from an Inertial Navigation System were conducted for both a quantitative and a qualitative assessment of the static/moving obstacle detection module and for the surface estimation approach. Reported results, from experiments using the KITTI database, demonstrate the applicability and efficiency of the proposed approach in urban scenarios.

Многоагентная система планирования движения мобильного робота на основе искусственных силовых полей

Многоагентная система планирования движения мобильного робота на основе искусственных силовых полей

Study of Moving Obstacle Detection at Railway Crossing by Machine Vision

Study of Moving Obstacle Detection at Railway Crossing by Machine Vision

1P1-J01 つくばチャレンジ2012における屋外自律ナビゲーションシステムの開発(3次元計測/センサフュージョン)

In this paper, we propose an autonomous navigation system that do not need detailed preinformation. To achieve robust traversability, our system adopts following technologies. The system involves a localization with GPS and dead reckoning. We integrate it by using Divided Difference Filter (DDF). Additionally our system also estimates traversability of road regions using a laser range finder (LRF). Our local map is made in consideration of pedestrians by a moving obstacles detection. The effectiveness of the proposed system is proved through some experiments.

Surrounding Moving Obstacle Detection for Autonomous Driving Using Stereo Vision

Detection and tracking surrounding moving obstacles such as vehicles and pedestrians are crucial for the safety of mobile robotics and autonomous vehicles. This is especially the case in urban driving scenarios. This paper presents a novel framework for surrounding moving obstacles detection using binocular stereo vision. The contributions of our work are threefold. Firstly, a multiview feature matching scheme is presented for simultaneous stereo correspondence and motion correspondence searching. Secondly, the multiview geometry constraint derived from the relative camera positions in pairs of consecutive stereo views is exploited for surrounding moving obstacles detection. Thirdly, an adaptive particle filter is proposed for tracking of multiple moving obstacles in surrounding areas. Experimental results from real-world driving sequences demonstrate the effectiveness and robustness of the proposed framework.

Geometric and Bayesian models for safe navigation in dynamic environments

Autonomous navigation in open and dynamic environments is an important challenge, requiring to solve several difficult research problems located on the cutting edge of the state of the art. Basically, these problems may be classified into three main categories: (a) SLAM in dynamic environments; (b) detection, characterization, and behavior prediction of the potential moving obstacles; and (c) online motion planning and safe navigation decision based on world state predictions. This paper addresses some aspects of these problems and presents our latest approaches and results. The solutions we have implemented are mainly based on the followings paradigms: multiscale world representation of static obstacles based on the wavelet occupancy grid; adaptative clustering for moving obstacle detection inspired on Kohonen networks and the growing neural gas algorithm; and characterization and motion prediction of the observed moving entities using Hidden Markov Models coupled with a novel algorithm for structure and parameter learning.

Improving backing-up manoeuvre safety with vision-based movement detection

Every year, backing-up crashes are responsible for hundreds of casualties in the world. In order to reduce this number, many automotive suppliers now provide ways for drivers to monitor the rear of their vehicle using sonar - or radar-based systems or wide angle cameras. Yet these systems still do not offer the performance required to consequently reduce the number of fatalities. To overcome the limitations of these systems, we have developed a real-time static obstacle detection system using a wide angle camera. We now propose to add moving obstacle detection and localisation to our camera-based system. Such system is the perfect candidate for next generation of automatic anti-collision systems. Our approach is based on camera movement compensation using inverse perspective mapping and probabilistic reasoning for movement detection. Using shape filtering, our approach can even limit detection to specific types of moving objects (pedestrians, cars etc.). We present the algorithms developed and the evaluation protocol used. We also show results of the system in typical urban situations, some in hard conditions (worst cases), and conclude on which future developments will bring performance improvements.(A)

Moving obstacle detection from a navigating robot

This paper presents a system that detects unexpected moving obstacles that appear in the path of a navigating robot, and estimates the relative motion of the object with respect to the robot. The system is designed for a robot navigating in a structured environment with a single wide-angle camera. The system uses polar mapping to simplify the segmentation of the moving object from the background. The polar mapping is performed with the focus of expansion as the center. A vision-based algorithm that uses the vanishing points of segments extracted from a scene in a few 3D orientations provides an accurate estimate of the robot orientation. In the transformed space qualitative estimate of moving obstacles is obtained by detecting the vertical motion of edges extracted in a few specified directions. Relative motion information about the obstacle is then obtained by computing the time to impact between the obstacles and robot from the radial component of the optical flow. The system was implemented and on an indoor mobile robot.

Moving obstacle detection and recognition by optical flow pattern analysis for mobile robots

—This paper presents a new idea for an obstacle recognition method for mobile robots by analyzing optical flow information acquired from dynamic images. First, the optical flow field is detected in image sequences from a camera on a moving observer and moving object candidates are extracted by using a normalized square residual error [focus of expansion (FOE) residual error] value that is calculated in the process of estimating the FOE. Next, the optical flow directions and intensity values are stored for the pixels involved in each candidate region to calculate the distribution width values around the principal axes of inertia and the direction of the principal axes. Finally, each candidate is classified into an object category that is expected to appear in the scene by comparing the proportion and the direction values with standard data ranges for the objects which are determined by preliminary experiments. Experimental results of car/bicycle/pedestrian recognition in real outdoor scenes have shown the effectiveness of the proposed method.