Analysis of three-dimensional scenes
A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.
1. A method for processing data, comprising:
receiving a depth map of a scene containing a background and one or more foreground objects that conceal and cast a shadow on parts of the background, the depth maps comprising a matrix of pixels, at least some of which have respective pixel depth values and correspond to respective locations in the scene;
using a digital processor, processing the depth map in the sequence so as to identify an area of the shadow, in which the pixels have no depth values in the depth map, with a foreground object that is adjacent to the identified area and casts the shadow in the area such that the identified area of the shadow includes only the pixels with no depth values that are located within a predefined maximum shadow width of the foreground object;
constructing, based on the depth map, a background model of the scene that includes the identified area of the shadow adjacent to the foreground object; and
segmenting the depth map using the background model.
2. The method according to claim 1 , wherein receiving the depth map comprises receiving a temporal sequence of depth maps, wherein processing the depth map comprises computing a shadow image indicating shadowed areas of the depth map, and wherein constructing the background model comprises updating the background model over the sequence of the depth maps while using the shadow image in controlling the updating.
3. The method according to claim 1 , wherein segmenting the depth map comprises generating a foreground map by removing, based on the background model, one or more background objects from the depth map, and identifying the foreground object in the foreground map.
4. Apparatus for processing data, comprising:
an imaging assembly, which is configured to produce a depth map of a scene containing a background and one or more foreground objects that conceal and cast a shadow on parts of the background, the depth maps comprising a matrix of pixels, at least some of which have respective pixel depth values and correspond to respective locations in the scene; and
a processor, which is configured to process the depth map so as to identify an area of the shadow, in which the pixels have no depth values in the depth map, with a foreground object that is adjacent to the identified area and casts the shadow in the area such that the identified area of the shadow includes only the pixels with no depth values that are located within a predefined maximum shadow width of the foreground object, to construct, based on the depth map, a background model of the scene that includes the identified area of the shadow adjacent to the foreground object, and to segment the depth map using the background model.
5. The apparatus according to claim 4 , wherein the imaging assembly is configured to produce a temporal sequence of depth maps, and wherein the processor is configured to compute a shadow image indicating shadowed areas of the depth map, and to update the background model over the sequence of the depth maps while using the shadow image in controlling the update.
6. The apparatus according to claim 4 , wherein the processor is configured to generate a foreground map by removing, based on the background model, one or more background objects from the depth map, and to identify the foreground object in the foreground map.
7. A computer software product, comprising a non-transitory computer-readable medium in which program instructions are stored, which instructions, when read by a computer, cause the computer to receive a depth map of a scene containing a background and one or more foreground objects that conceal and cast a shadow on parts of the background, the depth maps comprising a matrix of pixels, at least some of which have respective pixel depth values and correspond to respective locations in the scene,
wherein the instructions cause the computer to process the depth map so as to identify an area of the shadow, in which the pixels have no depth values in the depth map, with a foreground object that is adjacent to the identified area and casts the shadow in the area such that the identified area of the shadow includes only the pixels with no depth values that are located within a predefined maximum shadow width of the foreground object, to construct, based on the depth map, a background model of the scene that includes the identified area of the shadow adjacent to the foreground object, and to segment the depth map using the background model.
8. The product according to claim 7 , wherein the instructions cause the computer to receive a temporal sequence of depth maps, to compute a shadow image indicating shadowed areas of the depth map, and to update the background model over the sequence of the depth maps while using the shadow image in controlling the update.