Fusing disparate object signatures for salient object detection in video

Highlights：

• We employ object signatures from complementary channels to help each other in improving salient object detection in respective channels in a video.

• A learning-based method combines various appearance and motion cues is introduced to predict motion boundaries, which are stable for foreground object detection in complex scenes.

• Foreground weights that are computed according to the identified object signatures are used to estimate saliency maps.

• A fusion method, which depends on the saliency information and object signatures, is proposed to integrate saliency maps from different channels to form a higher-quality spatiotemporal saliency maps.