Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection-猫眼课题宝

DOI：

10.1609/aaai.v36i2.20074

发表时间：

2021-12

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Xianpeng Liu;Nan Xue;Tianfu Wu

单目3D目标检测的目的是在输入的单幅2D图像中定位3D包围盒。这是一个极具挑战性的问题，仍然是一个开放的问题，特别是在训练和/或推理中不能利用额外信息(例如，深度、激光雷达和/或多帧)的情况下。本文提出了一种简单而有效的单目三维目标检测公式，不需要利用任何额外信息。提出了学习单目背景的单目学习方法，作为训练中的辅助任务，辅助单目三维目标检测。其核心思想是利用图像中目标的3D包围盒，在训练中可以获得丰富的适定投影2D监督信号集，例如投影的角点关键点及其相对于2D包围盒中心的偏移向量，这些应该作为训练中的辅助任务来利用。提出的MonoCon是由测度论中的Cramer-Wold定理在较高水平上提出的。在实现上，它使用非常简单的端到端设计来证明学习辅助单目上下文的有效性，该设计包括三个组件：基于深度神经网络(DNN)的特征主干，用于学习3D包围盒预测中使用的基本参数的多个回归头分支，以及用于学习辅助上下文的多个回归头分支。训练结束后，为了提高推理效率，去掉了辅助上下文回归分支。在实验中，提出的MonoCon在Kitti基准测试中进行了测试(汽车、行人和骑自行车的人)。在汽车类别的排行榜上，它的表现优于所有现有技术，在行人和骑自行车的人身上，它在准确性方面也取得了类似的表现。由于设计简单，所提出的MonoCon方法获得了最快的推理速度，相比于38.7fps。我们的代码在https://git.io/MonoCon.上发布

Monocular 3D object detection aims to localize 3D bounding boxes in an input single 2D image. It is a highly challenging problem and remains open, especially when no extra information (e.g., depth, lidar and/or multi-frames) can be leveraged in training and/or inference. This paper proposes a simple yet effective formulation for monocular 3D object detection without exploiting any extra information. It presents the MonoCon method which learns Monocular Contexts, as auxiliary tasks in training, to help monocular 3D object detection. The key idea is that with the annotated 3D bounding boxes of objects in an image, there is a rich set of well-posed projected 2D supervision signals available in training, such as the projected corner keypoints and their associated offset vectors with respect to the center of 2D bounding box, which should be exploited as auxiliary tasks in training. The proposed MonoCon is motivated by the Cramer–Wold theorem in measure theory at a high level. In implementation, it utilizes a very simple end-to-end design to justify the effectiveness of learning auxiliary monocular contexts, which consists of three components: a Deep Neural Network (DNN) based feature backbone, a number of regression head branches for learning the essential parameters used in the 3D bounding box prediction, and a number of regression head branches for learning auxiliary contexts. After training, the auxiliary context regression branches are discarded for better inference efficiency. In experiments, the proposed MonoCon is tested in the KITTI benchmark (car, pedestrian and cyclist). It outperforms all prior arts in the leaderboard on the car category and obtains comparable performance on pedestrian and cyclist in terms of accuracy. Thanks to the simple design, the proposed MonoCon method obtains the fastest inference speed with 38.7 fps in comparisons. Our code is released at https://git.io/MonoCon.

Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection

文献摘要

相似文献