Multimodal Convolutional Neural Network for Object Detection Using RGB-D Images

This paper presents a new convolutional neural network architecture for performing object detection based on RGB-D images. The network is an extension of the Faster-RCNN network where we add an additional input network branch for processing the depth image. The network was evaluated on the SUN RGB-D dataset for object detection and we obtained a positive difference in mAP score of about 4%, compared to the original one.