Masked RCNN+ fast boosted tree classifier: a combination of deep learning technology for neural networks and classifier for pedestrian detection

Abstract

The most intriguing advancements brought by deep learning and neural networks is in the field of computer vision. We associate any problem that has an image or camera input to encompass problems within computer vision. Self-driving cars, MRI analysis, Mars exploration rovers, facial recognition systems, object detection and augmented reality are just a few breakthroughs in the field. In this paper we will take a look at ways to improve pedestrian detection by using Convolutional Neural Network (CNN) along with Region Proposal Network (RPN), Masked Region Based Convolutional Neural Network (RCNN) and Fast Boosted Tree Classifier. Our approach effectively recognizes objects in a picture while at the same time generating an excellent segmentation mask for each instance. The technique, called Mask R-CNN, expands Faster R-CNN by including a branch for predicting an item mask in parallel with the current branch for bouncing box recognitionn.