@inproceedings{641aee7e7a824e6e8b41864e01ff2010,
title = "MoNet3D: Towards accurate monocular 3d object localization in real time",
abstract = "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 drivingassistance system applications. Our code is publicly available at https://github.com/CQUlearningsystemgroup/YicongPeng.",
author = "Xichuan Zhou and Yicong Peng and Chunqiao Long and Fengbo Ren and Cong Shi",
note = "Funding Information: This work was supported by the National Natural Science Foundation of China under Contract 61971072. Publisher Copyright: {\textcopyright} 2020 by the Authors All rights reserved.; 37th International Conference on Machine Learning, ICML 2020 ; Conference date: 13-07-2020 Through 18-07-2020",
year = "2020",
language = "English (US)",
series = "37th International Conference on Machine Learning, ICML 2020",
publisher = "International Machine Learning Society (IMLS)",
pages = "11440--11449",
editor = "Hal Daume and Aarti Singh",
booktitle = "37th International Conference on Machine Learning, ICML 2020",
}