Stereo‐based all‐terrain obstacle detection using visual saliency

Abstract

This paper proposes a hybridization of two well-known stereo-based obstacle detection techniques for allterrain environments. While one of the techniques is employed for the detection of large obstacles, the other is used for the detection of small ones. This combination of techniques opportunistically exploits their complementary properties to reduce computation and improve detection accuracy. Being particularly computation intensive and prone to generate a high false-positive rate in the face of noisy three-dimensional point clouds, the technique for small obstacle detection is further extended in two directions. The goal of the first extension is to reduce both problems by focusing the detection on those regions of the visual field that detach more from the background and, consequently, are more likely to contain an obstacle. This is attained by means of spatially varying the data density of the input images according to their visual saliency. The second extension refers to the use of a novel voting mechanism, which further improves robustness. Extensive experimental results confirm the ability of the proposed method to robustly detect obstacles up to a range of 20 m on uneven terrain. Moreover, the model runs at 5 Hz on 640 × 480 stereo images. C

A feature matching and fusion-based positive obstacle detection algorithm for field autonomous land vehicles

“…Stereo camera is always employed to estimate the ground plane before detecting potential obstacles. 5 In the study of Santana et al, 5 a stereo-based obstacle detection approach is presented using visual saliency. In this approach, saliency map is generated from a single image, and a 3-D point cloud is generated from the stereo processing.…”

“…4 Positive obstacle detection is widely researched and many distinguished literatures have emerged recently. [5][6][7] In general, different kinds of sensors, such as thermal infrared camera, color camera, stereo, 2-D or 3-D LiDAR, or their combination, are employed to detect the obstacles. The thermal infrared camera is typically used to detect living organisms, such as animals at night.…”

“…Another algorithm is introduced in the article. 5 For a 640 Â 480 image working on a GPU, it costs about 200 ms to finish a frame. The aforementioned computing time is listed in Table 2.…”

On Exploiting Haptic Cues for Self-Supervised Learning of Depth-Based Robot Navigation Affordances

“…Typically, the volumetric signature of obstacles is used for their detection from range data acquired by either laser scanners [8,42,39,24] or binocular vision systems [22,30,34,32]. Monocular appearance cues are also useful when exploiting known structures from the environment, such as the existence of paths to be followed [33,28].…”

Two-Stage Obstacle Detection Based on Stereo Vision in Unstructured Environment

“…), which leads to a considerable computation cost. In [9], the synergistic use of visual saliency and SVR is proposed to speed up computation. The salience model is built based on the image directly obtained from the stereoscopic vision sensor.…”