FisheyeMultiNet: Real-time Multi-task Learning Architecture for Surround-view Automated Parking System
This addresses the need for efficient, full 360° sensing in low-speed automated parking systems for vehicles, though it appears incremental as it builds on existing multi-task learning approaches.
The paper tackles the problem of automated parking by developing FisheyeMultiNet, a real-time multi-task deep learning architecture for surround-view sensing, which runs at 15 fps on a low-power embedded system and detects objects, performs semantic segmentation, and soiling detection. It also releases a partial dataset of 5,000 images to encourage further research.
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}.