Depth from Camera Motion and Object Detection
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.
Code (2)
Tasks
Objectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
3D Object Aided Self-Supervised Monocular Depth Estimation
Monocular depth estimation has been actively studied in fields such as robot vision, autonomous driving, and 3D scene understanding. Given a sequence of color images, unsupervised learning methods based on the framework …
3D Object DetectionAutonomous DrivingDepth EstimationMonocular 3D Object Detection+5Monocular 3D Object Detection with Depth from Motion
Perceiving 3D objects from monocular inputs is crucial for robotic systems, given its economy compared to multi-sensor settings. It is notably difficult as a single image can not provide any clues for predicting absolute…
3D Object DetectionDepth EstimationMonocular 3D Object DetectionObject+2Choosing Smartly: Adaptive Multimodal Fusion for Object Detection in Changing Environments
Object detection is an essential task for autonomous robots operating in dynamic and changing environments. A robot should be able to detect objects in the presence of sensor noise that can be induced by changing lightin…
object-detectionObject DetectionSfM-Net: Learning of Structure and Motion from Video
We propose SfM-Net, a geometry-aware neural network for motion estimation in videos that decomposes frame-to-frame pixel motion in terms of scene and object depth, camera motion and 3D object rotations and translations. …
Motion EstimationObjectOptical Flow EstimationLearning Residual Flow as Dynamic Motion from Stereo Videos
We present a method for decomposing the 3D scene flow observed from a moving stereo rig into stationary scene elements and dynamic object motion. Our unsupervised learning framework jointly reasons about the camera motio…
Depth And Camera MotionMotion EstimationOptical Flow EstimationStereo Matching+2