Gated2Depth: Real-Time Dense Lidar From Gated Images
Gated2Depth: Real-Time Dense Lidar From Gated Images
复制标题
Gated2Depth：来自门控图像的实时密集激光雷达
DOI：
10.1109/iccv.2019.00159
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Felix Heide
中科院分区：
文献类型：
--
作者：
Tobias Gruber;Frank D. Julca;Mario Bijelic;W. Ritter;K. Dietmayer;Felix Heide
我们提出了一个成像框架，它将来自门控相机的三幅图像转换为高分辨率深度图，其深度精度可与脉冲激光雷达测量相媲美。由于机械上限制的角度采样率，现有的扫描激光雷达系统在大范围内实现低空间分辨率，将场景理解任务限制在具有密集采样的近距离集群中。此外，当今的脉冲激光雷达扫描仪成本高、功耗大、外形尺寸大，并且在存在强反向散射的情况下会失效。我们从点扫描出发，证明可以通过从三个门控图像中学习深度，将低成本 CMOS 门控成像仪转变为至少 80m 范围的密集深度相机。所提出的架构利用门控切片的语义上下文，并在不需要密集深度标签的情况下对合成鉴别器损失进行训练。扫描激光雷达系统的拟议替代方案是实时的，可以处理反向散射并在远距离提供密集的深度。我们通过模拟和在北欧行驶 4,000 多公里获得的真实数据来验证我们的方法。数据和代码可在 https://github.com/gruberto/Gated2Depth 获取。
We present an imaging framework which converts three images from a gated camera into high-resolution depth maps with depth accuracy comparable to pulsed lidar measurements. Existing scanning lidar systems achieve low spatial resolution at large ranges due to mechanically-limited angular sampling rates, restricting scene understanding tasks to close-range clusters with dense sampling. Moreover, today's pulsed lidar scanners suffer from high cost, power consumption, large form-factors, and they fail in the presence of strong backscatter. We depart from point scanning and demonstrate that it is possible to turn a low-cost CMOS gated imager into a dense depth camera with at least 80m range - by learning depth from three gated images. The proposed architecture exploits semantic context across gated slices, and is trained on a synthetic discriminator loss without the need of dense depth labels. The proposed replacement for scanning lidar systems is real-time, handles back-scatter and provides dense depth at long ranges. We validate our approach in simulation and on real-world data acquired over 4,000km driving in northern Europe. Data and code are available at https://github.com/gruberto/Gated2Depth.
DOI：
10.1109/cvpr.2017.596
发表时间：
2016-12
期刊：
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子：
--
作者：
Benjamin Ummenhofer;Huizhong Zhou;J. Uhrig;N. Mayer;Eddy Ilg;Alexey Dosovitskiy;T. Brox
通讯作者：
Benjamin Ummenhofer;Huizhong Zhou;J. Uhrig;N. Mayer;Eddy Ilg;Alexey Dosovitskiy;T. Brox