Method and apparatus for human detection in images

A computer-implemented method for human detection in images, the method comprising:

• subtracting, by a background subtraction module, a current image from a base image to obtain a delta image, the delta image comprising at least one object;
• filtering, by a noise filter module, stray noises and/or noise clusters from the delta image;
• marking and traversing, by an object detection module, a boundary of the at least one object;
• determining, by the object detection module, the at least one object as a valid object:
• if a length traversed along the boundary of the at least one object is greater than a pre-determined threshold value;
• and
• if an interior region of the at least one object is detected as solid;
• erasing, by a human recognition block, the interior region of the valid object and segmenting the boundary of the valid object into a pre-determined number of blocks;
• extracting and processing, by the human recognition block and a decision module, boundary features of the valid object to identify if the at least one object is a human being or not.

An apparatus for human detection in images, the apparatus comprising:

• a processor;
• a memory coupled to the processor, wherein the memory comprises a plurality of modules capable of being executed by the processor to perform operations, the plurality of modules comprising:
• a background subtraction module configured for subtracting a current image from a baseline image to obtain a delta image, the delta image comprising at least one object;
• a noise filter module configured for filtering stray noises and/or noise clusters from the delta image;
• an object detection module configured for marking and traversing a boundary of the at least one object;
• the object detection module further configured for determining the at least one object as valid object:
• if a length traversed along the boundary of the at least one object is greater than a pre-determined threshold value;
• and
• if an interior region of the at least one object is detected as being solid;
• a human recognition module configured for erasing the interior region of the at least one object and determining one or more pre-determined points on the boundary of the valid object;
• the human recognition module configured for determining one or more pre-determined parameters corresponding to said the one or more pre-determined points and ratios thereof;
• the human recognition module and a decision module configured for processing the ratios to identify if the at least one object is a human being or not.

An apparatus for human detection in images, the apparatus comprising:

• a processor;
• a memory coupled to the processor, wherein the memory comprises a plurality of modules capable of being executed by the processor to perform operations, the plurality of modules comprising:
• a background subtraction module configured for subtracting a current image from a base image to obtain a delta image, the delta image comprising at least one object;
• a noise filter module configured for filtering stray noises and/or noise clusters from the delta image;
• an objection detection module configured for marking and traversing a boundary of the at least one object;
• the object detection module further configured for determining the at least one object as valid object:
• if a length traversed along the boundary of the at least one object is greater than a pre-determined threshold value;
• and
• if an interior region of the at least one object is detected as solid;
• a human recognition module configured for erasing the interior region of the valid object and segmenting the boundary of the valid object into a pre-determined number of blocks;
• the human recognition module configured for extracting and processing boundary features of the valid object to identify if the at least one object is a human being or not.