Simultaneous Object Detection and Semantic Segmentation

TL;DR

This paper introduces a neural network architecture that performs object detection and semantic segmentation simultaneously, optimized for real-time processing in automated vehicles, achieving competitive accuracy on standard benchmarks.

Contribution

A novel neural network design that efficiently combines object detection and semantic segmentation for real-time autonomous vehicle applications.

Findings

Achieves 61.2% mean IoU on Cityscapes

Attains 69.3% average precision for cars on KITTI

Operates at around 10 Hz on 1 MP images

Abstract

Both object detection in and semantic segmentation of camera images are important tasks for automated vehicles. Object detection is necessary so that the planning and behavior modules can reason about other road users. Semantic segmentation provides for example free space information and information about static and dynamic parts of the environment. There has been a lot of research to solve both tasks using Convolutional Neural Networks. These approaches give good results but are computationally demanding. In practice, a compromise has to be found between detection performance, detection quality and the number of tasks. Otherwise it is not possible to meet the real-time requirements of automated vehicles. In this work, we propose a neural network architecture to solve both tasks simultaneously. This architecture was designed to run with around 10 Hz on 1 MP images on current hardware. Our approach achieves a mean IoU of 61.2% for the semantic segmentation task on the challenging Cityscapes benchmark. It also achieves an average precision of 69.3% for cars and 67.7% on the moderate difficulty level of the KITTI benchmark.