Due to the lack of depth information of images and poor detection accuracy in monocular 3D object detection, we proposed the instance depth for multi-scale monocular 3D object detection method. Firstly, to enhance the model's processing ability for different scale targets, a multi-scale perception module based on dilated convolution is designed, and the depth features containing multi-scale information are re-refined from both spatial and channel directions considering the inconsistency between feature maps of different scales. Firstly, we designed a multi-scale perception module based on dilated convolution to enhance the model's processing ability for different scale targets. The depth features containing multi-scale information are re-refined from spatial and channel directions considering the inconsistency between feature maps of different scales. Secondly, so as to make the model obtain better 3D perception, this paper proposed to use the instance depth information as an auxiliary learning task to enhance the spatial depth feature of the 3D target and use the sparse instance depth to supervise the auxiliary task. Finally, by verifying the proposed algorithm on the KITTI test set and evaluation set, the experimental results show that compared with the baseline method, the proposed method improves by 5.27\% in AP40 in the car category, effectively improving the detection performance of the monocular 3D object detection algorithm.
翻译:由于缺乏图像的深度信息,而且单立体3D物体探测的探测精确度差,我们建议采用多尺度单立体3D物体探测方法的试样深度。首先,为了提高模型对不同比例尺目标的处理能力,设计了一个基于放大变异的多尺度感知模块,并且考虑到不同比例尺的地貌图不一致,从空间和频道方向对包含多尺度信息的深度进行了重新界定。第一,我们设计了一个基于扩展变异的多尺度感知模块,以加强模型对不同比例尺目标的处理能力。包含多尺度信息的深度特征从空间和频道方向重新加以改进,考虑到不同比例尺特征图之间的不一致。第二,为了使模型获得更好的3D感知,本文件提议使用实例深度信息作为辅助学习任务,以加强3D目标的空间深度特征,并使用稀薄的体深来监督辅助任务。最后,通过核查KITTIT测试组和评估组的拟议算法和评估组,实验结果显示,与基线方法相比,改进汽车探测目标3号轨道的检测方法,通过5. AS. AN 有效改进了5. AS AS AS AR AR 的检测。