Method and apparatus for real-time pedestrian detection for urban driving

A computer-readable medium comprising computer-executable instructions for detecting the presence of one or more pedestrians in the vicinity of the vehicle, the instructions configured for:

• receiving a imagery of a scene from at least one image capturing device;
• deriving a depth map from the imagery;
• detecting a plurality of pedestrian candidate regions of interest (ROIs) from the depth map by matching each of the plurality of ROIs with a 3D human shape model;
• and
• classifying at least a portion of the candidate ROIs by employing a cascade of classifiers tuned for a plurality of depth bands and trained on a filtered representation of data within the portion of candidate ROIs to determine whether at least one pedestrian is proximal to the vehicle.

A system for detecting the presence of one or more pedestrians in the vicinity of the vehicle, comprising:

• at least one image capturing device for receiving imagery of a scene;
• at least one processor communicatively connected to the at least one image capturing device for:
• receiving the imagery of the scene from the image capturing device;
• deriving a depth map from said imagery;
• detecting a plurality of pedestrian candidate regions of interest (ROIs) from the depth map by matching each of the plurality of ROIs with a 3D human shape model;
• and
• classifying at least a portion of the candidate ROIs by employing a cascade of classifiers tuned for a plurality of depth bands and trained on a filtered representation of data within the portion of candidate ROIs to determine whether at least one pedestrian is proximal to the vehicle.