A Comparison of Bottom-Up Models for Spatial Saliency Predictions in Autonomous Driving

Abstract

Bottom-up saliency models identify the salient regions of an image based on features such as color, intensity and orientation. These models are typically used as predictors of human visual behavior and for computer vision tasks. In this paper, we conduct a systematic evaluation of the saliency maps computed with four selected bottom-up models on images of urban and highway traffic scenes. Saliency both over whole images and on object level is investigated and elaborated in terms of the energy and the entropy of the saliency maps. We identify significant differences with respect to the amount, size and shape-complexity of the salient areas computed by different models. Based on these findings, we analyze the likelihood that object instances fall within the salient areas of an image and investigate the agreement between the segments of traffic participants and the saliency maps of the different models. The overall and object-level analysis provides insights on the distinctive features of salient areas identified by different models, which can be used as selection criteria for prospective applications in autonomous driving such as object detection and tracking.

A Path Planning Method with Perception Optimization Based on Sky Scanning for UAVs

“…Deep learning methods for object detection have been applied in many areas including automatic driving, medical application, urban research, and so on [ 3 , 4 , 5 ]. These kinds of technology can also be utilized on scenes understanding for path planning.…”

Influence of the Weld Joint Position on the Mechanical Stress Concentration in the Construction of the Alternative Skid Car System’s Skid Chassis

“…Nevertheless, it is not excluded that the combination of the human factor (portrayed by the driver) and autonomous vehicles on real road traffic can be of great help in a condition that carries a significant risk of collision [1]. Therefore, it is necessary to develop new or to improve existing car control systems [2][3][4][5][6][7][8], with the help of both existing data, and the theories and tools at our disposal, and proceed with the verification and validation of results compared to those obtained experimentally in laboratory conditions. This applied approach results in a rapid development while maintaining financial efficiency, unlike in cases in which fundamental research requires substantial financial resources.…”