A Brain-inspired Method for Occluded 3D Object Recognition

Recently, 3D object recognition has been widely applied in various practical scenes and several methods were proposed for this task. Though these methods have made great progresses in 3D object recognition, they perform much poorly for occluded 3D objects. As a comparison, humans recognize 3D objects well, no matter the object is occluded or non-occluded. Some brain science researches demonstrated that humans recognize 3D objects by the process from sensory input to proto-objects representation, object-file representation, and finally, recognition. We therefore propose a novel brain-inspired 3D multi-view object recognition network (BiMVNet) to realize this process by mimicing the human visual system with visual working memory and knowledge. Specifically, BiMVNet imitates the human visual cortex to extract the proto-objects representation, the human visual working memory and knowledge to extract the object-file representation, and finally recognizes 3D objects based on the object-file representation. Furthermore, we propose an occluded 3D object dataset Occ-ModelNet40 based on the popular ModelNet40 dataset to thoroughly evaluate BiMVNet. Experiments on Occ-ModelNet40 and ModelNet40 show that our BiMVNet outperforms existing methods on both occluded and non-occluded object recognition.