Efficient object detection based on selective attention

• An orientation-only and most-refined-scale-only attention model is proposed.
• Saccade map based on attention is proposed to simulate the saccade in vision.
• Heuristic feature selection can select out good features more stably.
• Object detection with saccade map is efficient.

In this paper, we make use of biologically inspired selective attention to improve the efficiency and performance of object detection under clutter. At first, we propose a novel bottom-up attention model. We argue that heuristic feature selection based on bottom-up attention can stably select out invariant and discriminative features. With these selected features, performance of object detection can be improved apparently and stably. Then we propose a novel concept of saccade map based on bottom-up attention to simulate the saccade (eye movements) in vision. Sliding within saccade map to detect object can significantly reduce computational complexity and apparently improve performance because of the effective filtering for distracting information. With these ideas, we present a general framework for object detection through integrating bottom-up attention. Through evaluating on UIUC cars and Weizmann–Shotton horses we show state-of-the-art performance of our object detection model.

Figure optionsDownload as PowerPoint slide