MoNet3D: Towards Accurate Monocular 3D Object Localization in Real Time
This addresses the problem of accurate and fast 3D object detection from monocular images for advanced driving-assistance systems, representing an incremental improvement with specific gains.
The paper tackles monocular 3D object localization by proposing MoNet3D, which incorporates spatial geometric correlations to improve accuracy, achieving 96.25% depth and 94.74% horizontal coordinate accuracy on KITTI and real-time processing at 27.85 FPS.
Monocular multi-object detection and localization in 3D space has been proven to be a challenging task. The MoNet3D algorithm is a novel and effective framework that can predict the 3D position of each object in a monocular image and draw a 3D bounding box for each object. The MoNet3D method incorporates prior knowledge of the spatial geometric correlation of neighbouring objects into the deep neural network training process to improve the accuracy of 3D object localization. Experiments on the KITTI dataset show that the accuracy for predicting the depth and horizontal coordinates of objects in 3D space can reach 96.25\% and 94.74\%, respectively. Moreover, the method can realize the real-time image processing at 27.85 FPS, showing promising potential for embedded advanced driving-assistance system applications. Our code is publicly available at https://github.com/CQUlearningsystemgroup/YicongPeng.