人工智能
计算机视觉
视觉里程计
计算机科学
水准点(测量)
单眼
最小边界框
跳跃式监视
目标检测
移动机器人
里程计
运动(物理)
机器人
模式识别(心理学)
图像(数学)
地理
大地测量学
作者
Brent Griffin,Jason J. Corso
标识
DOI:10.1109/cvpr46437.2021.00145
摘要
This paper addresses the problem of learning to estimate the depth of detected objects given some measurement of camera motion (e.g., from robot kinematics or vehicle odometry). We achieve this by 1) designing a recurrent neural network (DBox) that estimates the depth of objects using a generalized representation of bounding boxes and uncalibrated camera movement and 2) introducing the Object Depth via Motion and Detection Dataset (ODMD). ODMD training data are extensible and configurable, and the ODMD benchmark includes 21,600 examples across four validation and test sets. These sets include mobile robot experiments using an end-effector camera to locate objects from the YCB dataset and examples with perturbations added to camera motion or bounding box data. In addition to the ODMD benchmark, we evaluate DBox in other monocular application domains, achieving state-of-the-art results on existing driving and robotics benchmarks and estimating the depth of objects using a camera phone.
科研通智能强力驱动
Strongly Powered by AbleSci AI