TY - GEN
T1 - Depth from Camera Motion and Object Detection
AU - Griffin, Brent A.
AU - Corso, Jason J.
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85122832867&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85122832867&partnerID=8YFLogxK
U2 - 10.1109/CVPR46437.2021.00145
DO - 10.1109/CVPR46437.2021.00145
M3 - Conference contribution
AN - SCOPUS:85122832867
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1397
EP - 1406
BT - Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
T2 - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
Y2 - 19 June 2021 through 25 June 2021
ER -