Pedestrian Detection with Simplified Depth Prediction
Pedestrian Detection with Simplified Depth Prediction
复制标题
具有简化深度预测的行人检测
DOI：
10.1109/itsc.2018.8569987
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
C. Bhat
中科院分区：
文献类型：
--
作者：
Taewan Kim;M. Motro;P. Lavieri;Saharsh Samir Oza;Joydeep Ghosh;C. Bhat
虽然RGB摄像头、雷达和激光雷达是智能车辆系统的常用传感器，但对其传感输出的实时联合推理仍然具有挑战性。此外，高分辨率LIDAR在成本和计算方面都是昂贵的。本文提出了一种基于深度学习的行人检测算法，该算法采用RGB图像和低分辨率LIDAR数据，并将图像中的对象检测结果作为二维边界框以及检测到的对象的距离返回。所提出的网络成本要低得多，但精度与之前的深度网络相当，联合收割机结合了这些传感器，使用LIDAR数据的图像或体素表示来直接预测3D位置和形状。为了训练该网络，创建了一个新的数据集，其中包含来自低端相机的注册信息，16层LIDAR，以及通过全球导航卫星系统（GNSS）传感器和固定塔估计行人位置生成的相应地面真实距离值。该数据集的公开发布是这一努力的额外贡献。
Though RGB Cameras, Radar and LIDARs are popular sensors for intelligent vehicle systems, real-time joint inference on their sensory outputs remains challenging. Moreover, high-resolution LIDAR is expensive both in terms of cost and computation. This paper presents a deep learning-based pedestrian detection algorithm that takes both RGB image and lower-resolution LIDAR data and returns object detections in the image as 2-D bounding boxes, plus the distances of the detected objects. The proposed network is much less expensive but comparable in accuracy to previous deep networks that combine these sensors use image-like or voxel representations of LIDAR data to directly predict 3D positions and shapes. To train this network, a new dataset was created, containing register information from low-end camera a 16-layer LIDAR, and corresponding ground truth distance values generated by estimating the position of pedestrians from global navigation satellite system (GNSS) sensors and a fixed tower. The public release of this dataset is an additional contribution of this effort.