A Salient Object Detection Algorithm Based on Hierarchical Cognitive Mechanism

Abstract

The key of salient object detection is to extract the most attractive area in the scene. This paper fully explores the hierarchical cognitive mechanism of visual information, combines color contrast and depth contrast, and puts forward a salient object detection algorithm for the RGB-D image. Three saliency maps were prepared, namely, initial saliency map, middle saliency map and advanced saliency map. The three maps were then fused into a final saliency map. The proposed method was compared with six popular salient object detection methods on three RGB-D image datasets. The comparison shows that our algorithm achieved the best results in accuracy, recall rate and F-value. The research findings shed important new light on salient object detection in RGB-D images.

Sliding Mode Control of Flexible Articulated Manipulator Based on Robust Observer

“…e system behaviors are complex and dynamic due to load variations, uncertain external perturbations, and inherent vibrations [1][2][3]. Hence, flexible manipulators can hardly be modelled or measured accurately, calling for a well-designed controller [4][5][6][7][8]. Against this backdrop, it is theoretically and practically significant to explore the response speed and control accuracy of trajectory tracking for the double-linked flexible-joint manipulator [9].…”