Pixel Level Instance Segmentation using Single Shot Detectors and Semantic Segmentation Networks

Abstract

Object detection algorithms are vital in computer vision applications especially the one regarding segmentation of objects in a scene. Instance segmentation using mask RCNN is the state of the art computer vision application using deep neural networks. However it has a complex pipeline for training and real-time testing. Single shot detectors based on CNN such as YOLO are robust in real time object detection compared to Faster RCNN. Combining convolutional networks for semantic segmentation along with single shot object detectors can give superior instance segmentation in real time at less computational complexity. Independent training of instance detection and segmentation networks makes it possible to create application specific pipelines based on context. Lighter architecture using single shot detectors and segmentation networks reduces latency on common processors thereby achieving higher frame rate. Class specific training of detectors improves the average precision of detection. The entire architecture is developed in python over Keras deeplearning framework.OpenCV library is used to render and process the input and output images.