System and method for real-time detection of objects in motion

A system for performing real-time detection of objects in motion, the system comprising:

• a video receiver configured to receive an input video stream from a camera;
• a motion detector configured to detect if a motion has occurred in a current frame of the input video stream based on pixel values of the current frame and one or more previous frames of the input video stream, and outputs the current frame if the motion has been detected therein;
• an object recognizer configured to receive and detect a moving object in the current frame using a machine learning algorithm;
• a display device configured to display the detected moving object;
• and
• an object tracking module configured to:
• simultaneously track a location of the detected moving object within corresponding frame, from latest co-ordinates of the detected moving object, while object recognition continues to recognize one or more of the detected moving objects;
• generate a tracking box and overlay the tracking box on the detected moving object and then transmit the video to the display device;
• and
• continue the tracking of the detected moving object till the object recognition continues for corresponding one or more of the detected moving objects.

A surveillance camera system, comprising:

• a camera;
• a display device;
• a memory to store one or more instructions;
• a processor communicatively coupled to the camera, display, and the memory, wherein the processor is configured to execute the one or more instructions of the memory to:
• receive an input video stream from the camera;
• detect if a motion has occurred in a current frame of the input video stream based on pixel values of the current frame and one or more previous frames of the input video stream;
• provide the current frame for object detection if the motion has been detected therein;
• detect a moving object in the current frame using a machine learning algorithm;
• transmit the video to the display device for displaying the detected moving object;
• simultaneously track the location of the detected moving object within corresponding frame, while object recognition continues to recognize one or more of the detected moving objects;
• generate a tracking box and overlay the tracking box on the detected moving object and then transmit the video to the display;
• and
• continue the tracking of the detected moving object till the object recognition continues for corresponding one or more of the detected moving objects.

A computer programmable product stored on a non-transitory computer readable medium for performing real-time detection of objects in motion, the computer programmable product comprising a set of instructions, the set of instructions when executed by a processor causes the processor to:

• receive an input video stream from a camera;
• detect if a motion has occurred in a current frame of the input video stream based on pixel values of the current frame and one or more previous frames of the input video stream;
• provide the current frame for object detection if the motion has been detected therein;
• detect a moving object in the current frame using a machine learning algorithm;
• transmit the video to the display device for displaying the detected moving object;
• simultaneously track a location of the detected moving object within corresponding frame from latest co-ordinates of the detected moving object, while object recognition continues to recognize one or more of the detected moving objects;
• generate a tracking box and overlay the tracking box on the detected moving object and then transmit the video to the display device;
• and
• continue the tracking of the detected moving object till the object recognition continues for corresponding one or more of the detected moving objects.