Shape-Aware Monocular 3D Object Detection

TL;DR

This paper introduces a shape-aware monocular 3D object detection model that integrates instance segmentation to improve detection accuracy, especially for occluded objects, and proposes a new evaluation metric for better assessment.

Contribution

The paper presents a novel single-stage monocular 3D detection model with an integrated shape awareness mechanism and introduces the ADS metric for more effective evaluation.

Findings

Outperforms baseline on existing and new metrics

Maintains real-time detection efficiency

Improves detection of occluded and truncated objects

Abstract

The detection of 3D objects through a single perspective camera is a challenging issue. The anchor-free and keypoint-based models receive increasing attention recently due to their effectiveness and simplicity. However, most of these methods are vulnerable to occluded and truncated objects. In this paper, a single-stage monocular 3D object detection model is proposed. An instance-segmentation head is integrated into the model training, which allows the model to be aware of the visible shape of a target object. The detection largely avoids interference from irrelevant regions surrounding the target objects. In addition, we also reveal that the popular IoU-based evaluation metrics, which were originally designed for evaluating stereo or LiDAR-based detection methods, are insensitive to the improvement of monocular 3D object detection algorithms. A novel evaluation metric, namely average depth similarity (ADS) is proposed for the monocular 3D object detection models. Our method outperforms the baseline on both the popular and the proposed evaluation metrics while maintaining real-time efficiency.