High accuracy monocular moving object localization

1. A method for moving object localization, comprising:

estimating a ground plane in a video frame based on a detected object within the video frame and monocular structure-from-motion (SFM) information;

computing object pose for objects in the frame based on the SFM information using dense feature tracking; and

determining a three-dimensional location for the detected object based on the estimated ground plane and the computed object pose;

wherein determining the three-dimensional location comprises a Levenberg-Marquardt optimization that finds a three-dimensional bounding box that minimizes a cost function;

wherein the cost function is:

ε=ε′ SFM +λ o ε′ obj +λ p ε′ prior

where ε′ SFM is a cost from SFM, ε′ obj is a cost from object bounding boxes, ε′ prior is a prior from the combined smoothness and object size priors, and λ o and λ p are weighting coefficients.

2. The method of claim 1 , wherein determining the three-dimensional location for the detected object is based on SFM cues, bounding box cues, and object detection cues.

3. The method of claim 1 , wherein dense feature tracking comprises determining an object pose based on dense intensity alignment and tracking dense features based on an epipolar guided optical flow.

4. The method of claim 1 , wherein motion segmentation and complex inference are not used to speed object localization.

5. A non-transitory storage medium with instructions enabling a computer to carry out the following,

estimating a ground plane in a video frame based on a detected object within the video frame and monocular structure-from-motion (SFM) information,

computing an object pose for objects in the frame based on the SFM information using dense feature tracking, and

determining a three-dimensional location for the detected object based on the estimated ground plane and the computed object pose;

wherein determining the three-dimensional location comprises using a Levenberg-Marquardt optimization that finds a three-dimensional bounding box that minimizes a cost function;

wherein the cost function is:

ε=ε′ SFM +λ o ε′ obj +λ p ε′ prior

where ε′ SFM is a cost from SFM, ε′ obj is a cost from object bounding, ε′ prior is a prior from the combined smoothness and object size priors, and λ o and λ p are weighting coefficients.

6. The non-transitory storage medium of claim 5 , wherein the processor is configured to determine the three-dimensional location for the detected object based on SFM cues, bounding box cues, and object detection cues.

7. The non-transitory storage medium of claim 5 , wherein the processor is configured to track dense features by determining an object pose based on dense intensity alignment and tracking dense features based on an epipolar guided optical flow.

8. The non-transitory storage medium of claim 5 , wherein the processor is configured not to use motion segmentation or complex inference to speed object localization.