Segment and Cut: A Simpler Method for Extracting Bounding-Boxes for Object Detection

Date

2019-05

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Object detectors that are based on bounding-box regression are complex and require a lot of refinement to get good results. Is there a simpler way of doing object detection? To that end, I present a new method for object detection where you first segment an image, and then cut each object from the segmentation to produce its bounding box. The key to this method is that it uses only ground truth bounding box data to generate the ground truth segmentation mask, rather than using a semantic-segmentation mask which are pixel-perfect. Additionally, I present a modified Flood Fill algorithm for the cutting task. Using this method, I eliminate the need for bounding-box regression, anchor-boxes, region proposal methods and all of their associated complexities. Experiments show that my method gets competitive performance on the WIDER Face dataset with full-size images and runs between 30 and 50 FPS when using 640x480 pixel images.

Description

Keywords

Object detection, Image Segmentation, Face recognition

Citation