FisheyeMultiNet: Real-time Multi-task Learning Architecture for Surround-view Automated Parking System

Abstract

Automated Parking is a low speed manoeuvring scenario which is quite unstructured and complex, requiring full 360° near-field sensing around the vehicle. In this paper, we discuss the design and implementation of an automated parking system from the perspective of camera based deep learning algorithms. We provide a holistic overview of an industrial system covering the embedded system, use cases and the deep learning architecture. We demonstrate a real-time multi-task deep learning network called FisheyeMultiNet, which detects all the necessary objects for parking on a low-power embedded system. FisheyeMultiNet runs at 15 fps for 4 cameras and it has three tasks namely object detection, semantic segmentation and soiling detection. To encourage further research, we release a partial dataset of 5,000 images containing semantic segmentation and bounding box detection ground truth via WoodScape project \cite{yogamani2019woodscape}.

Accepted for publication at Irish Machine Vision and Image Processing (IMVIP) 2019

References in corpus (4)

• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
• Computer vision in automated parking systems: Design, implementation and challenges
• AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving