Obstacle Classification and 3D Measurement in Unstructured Environments Based on ToF Cameras

This study proposes an obstacle detection method that uses depth information to allow the visually impaired to avoid obstacles when they move in an unfamiliar environment. The system is composed of three parts: scene detection, obstacle detection and a vocal announcement. This study proposes a new method to remove the ground plane that overcomes the over-segmentation problem. This system addresses the over-segmentation problem by removing the edge and the initial seed position problem for the region growth method using the Connected Component Method (CCM). This system can detect static and dynamic obstacles. The system is simple, robust and efficient. The experimental results show that the proposed system is both robust and convenient.

“…Infrared rays are easily affected by sunlight [ 44 ]. The Kinect sensor depends on emitted infrared rays to generate a depth map, so the Kinect sensor has some hardware limitations.…”

Section: Resultsmentioning

confidence: 99%

An Indoor Obstacle Detection System Using Depth Information and Region Growth

Huang

Hsieh

Yeh

2015

“…An enhanced CHT [ 9 ] is employed for estimating the trajectory of a spherical target in three dimensions to improve tracking accuracy. For robotic navigation in unstructured environments, a method based on ToF cameras [ 10 ] was provided for 3D obstacle detection and classification. Meanwhile, in the area of industrial and daily application [ 11 ], the robot mechanism presents a promising prospect.…”

Section: Related Workmentioning

confidence: 99%

Pixel-Wise Crack Detection Using Deep Local Pattern Predictor for Robot Application

Wang

2018

Robotic vision-based crack detection in concrete bridges is an essential task to preserve these assets and their safety. The conventional human visual inspection method is time consuming and cost inefficient. In this paper, we propose a robust algorithm to detect cracks in a pixel-wise manner from real concrete surface images. In practice, crack detection remains challenging in the following aspects: (1) detection performance is disturbed by noises and clutters of environment; and (2) the requirement of high pixel-wise accuracy is difficult to obtain. To address these limitations, three steps are considered in the proposed scheme. First, a local pattern predictor (LPP) is constructed using convolutional neural networks (CNN), which can extract discriminative features of images. Second, each pixel is efficiently classified into crack categories or non-crack categories by LPP, using as context a patch centered on the pixel. Lastly, the output of CNN—i.e., confidence map—is post-processed to obtain the crack areas. We evaluate the proposed algorithm on samples captured from several concrete bridges. The experimental results demonstrate the good performance of the proposed method.

“…In general, environmental understanding is the essential prerequisite for ensuring the stable and robust operations of autonomous robots [ 7 ], and many methods have been proposed up to now [ 8 , 9 ]. Optical camera-based methods have become very popular [ 10 , 11 ]. However, camera-based methods have several limitations such as the lack of geospatial and reflectivity intensity information, as well as image distortions and illumination variations.…”

Section: Introductionmentioning

confidence: 99%

Novel Laser-Based Obstacle Detection for Autonomous Robots on Unstructured Terrain

Chen

Liu

et al. 2020

Obstacle detection is one of the essential capabilities for autonomous robots operated on unstructured terrain. In this paper, a novel laser-based approach is proposed for obstacle detection by autonomous robots, in which the Sobel operator is deployed in the edge-detection process of 3D laser point clouds. The point clouds of unstructured terrain are filtered by VoxelGrid, and then processed by the Gaussian kernel function to obtain the edge features of obstacles. The Euclidean clustering algorithm is optimized by super-voxel in order to cluster the point clouds of each obstacle. The characteristics of the obstacles are recognized by the Levenberg–Marquardt back-propagation (LM-BP) neural network. The algorithm proposed in this paper is a post-processing algorithm based on the reconstructed point cloud. Experiments are conducted by using both the existing datasets and real unstructured terrain point cloud reconstructed by an all-terrain robot to demonstrate the feasibility and performance of the proposed approach.