Objectness Algorithm Based on Multiscale Local Extremum and Edge Detection

Aiming to promote the efficiency of object detection, the objectness was introduced to preanalyze the potential location of objects instead of the sliding window strategy with the complex features. Based on the multiscale local extremum and edge detection, an objectness method was proposed to leverage the efficiency. First, mean filter was used to obtain the local extremum on the multiscale gradient feature maps.According to these local extremums, coarse object proposals are extracted on the original RBG image.Second, the objectness score of each coarse object proposal was calculated based on the edge feature. Finally,redundant proposals were removed by nonmaximum suppression with the scale information and the objectness score. The comparative experiment results in the public datasets (PASCAL VOC and ILSVRC 2014) demonstrated that the recall rate of our method achieved over 97% (PASCAL) and 98% (ILSVRC 2014) with 1000 proposals respectively. Furthermore, the recall rate of the top one proposal was improved too.