LineMarkNet: Line Landmark Detection for Valet Parking

TL;DR

LineMarkNet is a deep learning system designed for accurate, real-time detection of line landmarks in valet parking, combining multi-view fusion, hierarchical reasoning, and temporal filtering to improve autonomous parking accuracy and stability.

Contribution

The paper introduces a lightweight, multi-task deep network for line landmark detection that fuses surround-view features into a unified BEV space and employs hierarchical graph reasoning, with a new dataset for validation.

Findings

Achieves superior accuracy over existing methods.

Operates in real-time on Qualcomm 820A platform.

Provides stable, smooth line detection through temporal filtering.

Abstract

We aim for accurate and efficient line landmark detection for valet parking, which is a long-standing yet unsolved problem in autonomous driving. To this end, we present a deep line landmark detection system where we carefully design the modules to be lightweight. Specifically, we first empirically design four general line landmarks including three physical lines and one novel mental line. The four line landmarks are effective for valet parking. We then develop a deep network (LineMarkNet) to detect line landmarks from surround-view cameras where we, via the pre-calibrated homography, fuse context from four separate cameras into the unified bird-eye-view (BEV) space, specifically we fuse the surroundview features and BEV features, then employ the multi-task decoder to detect multiple line landmarks where we apply the center-based strategy for object detection task, and design our graph transformer to enhance the vision transformer with hierarchical level graph reasoning for semantic segmentation task. At last, we further parameterize the detected line landmarks (e.g., intercept-slope form) whereby a novel filtering backend incorporates temporal and multi-view consistency to achieve smooth and stable detection. Moreover, we annotate a large-scale dataset to validate our method. Experimental results show that our framework achieves the enhanced performance compared with several line detection methods and validate the multi-task network's efficiency about the real-time line landmark detection on the Qualcomm 820A platform while meantime keeps superior accuracy, with our deep line landmark detection system.