29 January 2021 Training a thin and shallow lane detection network with self-knowledge distillation
Xuerui Dai, Xue Yuan, Xueye Wei
Author Affiliations +
Abstract

With modern science and technology development, vehicles are equipped with intelligent driver assistant systems, of which lane detection is a key function. These complex detection structures (either wide or deep) are investigated to boost the accuracy and overcome the challenges in complicated scenarios. However, the computation and memory storage cost will increase sharply, and the response time will also increase. For resource-constrained devices, lane detection networks with a low cost and short inference time should be implemented. To get more accurate lane detection results, the large (deep and wide) detection structure is framed for high-dimensional and highly robust features, and deep supervision loss is applied on different resolutions and stages. Despite the high-precision advantage, the large detection network cannot be used for embedded devices directly because of the demand for memory and computation. To make the network thinner and lighter, a general training strategy, called self-knowledge distillation (SKD), is proposed. It is different from classical knowledge distillation; there are no independent teacher-student networks, and the knowledge is distilled itself. To evaluate more comprehensively and precisely, a new lane data set is collected. The Caltech Lane date set and TuSimple lane data set are also used for evaluation. Experiments further prove that a small student network and large teacher network have a similar detection accuracy via SKD, and the student network has a shorter inference time and lower memory usage. Thus it can be applied for resource-limited devices flexibly.

© 2021 SPIE and IS&T 1017-9909/2021/$28.00© 2021 SPIE and IS&T
Xuerui Dai, Xue Yuan, and Xueye Wei "Training a thin and shallow lane detection network with self-knowledge distillation," Journal of Electronic Imaging 30(1), 013004 (29 January 2021). https://doi.org/10.1117/1.JEI.30.1.013004
Received: 18 June 2020; Accepted: 4 January 2021; Published: 29 January 2021
Lens.org Logo
CITATIONS
Cited by 2 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Network architectures

Video

Image segmentation

Image resolution

Intelligence systems

Roads

Convolution

RELATED CONTENT

A closer look at U-net for road detection
Proceedings of SPIE (August 09 2018)
Approach for counting vehicles in congested traffic flow
Proceedings of SPIE (February 25 2005)
Automated counting of pedestrians
Proceedings of SPIE (September 16 1994)
Light and fast multiple object tracking based on light...
Proceedings of SPIE (October 05 2021)

Back to Top