VEHICLE CONTROL

From a sequence of frames of video data including a start frame followed by intermediate frames followed by an end frame, some of the intermediate frames are identified as a first subset of frames and others of the intermediate frames are identified as a second subset of frames. The second subset of frames includes a target object in an environment. In the frames of the second subset, respective sets of pixels associated with the target object are identified. Based on timestamp offsets of frames in the first subset of frames and frames in the second set of frames, the frames in the first subset are augmented by injecting the respective sets of pixels from the second subset of frames to corresponding frames in the first subset.