MVM3Det: A Novel Method for Multi-view Monocular 3D Detection

TL;DR

MVM3Det is a new multi-view monocular 3D detection method that accurately estimates object position and orientation by integrating multi-view features, addressing occlusion and confusion issues, and demonstrating competitive results on new and existing datasets.

Contribution

The paper introduces MVM3Det, a novel approach for multi-view monocular 3D detection that effectively estimates position and orientation despite feature and label confusion.

Findings

Achieves competitive results on MVM3D and WildTrack datasets.

Introduces a new dataset for multi-view 3D detection.

Proposes feature orthogonal transformation and perspective pooling techniques.

Abstract

Monocular 3D object detection encounters occlusion problems in many application scenarios, such as traffic monitoring, pedestrian monitoring, etc., which leads to serious false negative. Multi-view object detection effectively solves this problem by combining data from different perspectives. However, due to label confusion and feature confusion, the orientation estimation of multi-view 3D object detection is intractable, which is important for object tracking and intention prediction. In this paper, we propose a novel multi-view 3D object detection method named MVM3Det which simultaneously estimates the 3D position and orientation of the object according to the multi-view monocular information. The method consists of two parts: 1) Position proposal network, which integrates the features from different perspectives into consistent global features through feature orthogonal transformation to estimate the position. 2) Multi-branch orientation estimation network, which introduces feature perspective pooling to overcome the two confusion problems during the orientation estimation. In addition, we present a first dataset for multi-view 3D object detection named MVM3D. Comparing with State-Of-The-Art (SOTA) methods on our dataset and public dataset WildTrack, our method achieves very competitive results.