Fast object detection method based on deformable part model (DPM)
First Claim
1. A fast object detection method based on a deformable part model (DPM) implemented by an object detection system, comprising:
- importing a trained classifier for object detection;
receiving an image frame from a plurality of image frames in a video captured by a camera;
identifying candidate regions in the image frame that may contain at least one object via objectness measure based on Binarized Normed Gradients (BING), the candidate regions being a subpart of the received image frame, wherein the objectness measure quantifies how likely it is for a region in the image frame to contain an object as opposed to backgrounds;
calculating Histogram of Oriented Gradients (HOG) feature pyramid of the image frame;
performing DPM detection for the identified candidate regions that may contain the at least one object based on the calculated HOG feature pyramid;
labeling the at least one detected object using at least one rectangle box via non-maximum suppression (NMS);
processing a next frame from the plurality of frames in the captured video until the video ends; and
outputting object detection results,wherein;
the fast object detection method is integrated with a LED lighting device;
a model for an object with n parts is formally defined by (n+2)-tuple (F0, P1 , . . . , Pn, b), wherein F0 is a root filter, Pi is a model for a i-th part and b is a real-valued bias term, n being an integer; and
provided that a location of each filter in a feature pyramid is (p0 , . . . , pn), and pi=(xi, yi, li) specifies a level and position of the i-th filter, a score of a window is defined by;
1 Assignment
0 Petitions
Accused Products
Abstract
A fast object detection method based on deformable part model (DPM) is provided. The method includes importing a trained classifier for object detection, receiving an image frame from a plurality of frames in a video captured by a camera, and identifying regions possibly containing at least one object via objectness measure based on Binarized Normed Gradients (BING). The method also includes calculating Histogram of Oriented Gradients (HOG) feature pyramid of the image frame, performing DPM detection for the identified regions possibly containing the at least one object, and labeling the at least one detected object using at least one rectangle box via non-maximum suppression (NMS). Further, the method includes processing a next frame from the plurality of frames in the captured video until the video ends and outputting object detection results.
31 Citations
9 Claims
-
1. A fast object detection method based on a deformable part model (DPM) implemented by an object detection system, comprising:
-
importing a trained classifier for object detection; receiving an image frame from a plurality of image frames in a video captured by a camera; identifying candidate regions in the image frame that may contain at least one object via objectness measure based on Binarized Normed Gradients (BING), the candidate regions being a subpart of the received image frame, wherein the objectness measure quantifies how likely it is for a region in the image frame to contain an object as opposed to backgrounds; calculating Histogram of Oriented Gradients (HOG) feature pyramid of the image frame; performing DPM detection for the identified candidate regions that may contain the at least one object based on the calculated HOG feature pyramid; labeling the at least one detected object using at least one rectangle box via non-maximum suppression (NMS); processing a next frame from the plurality of frames in the captured video until the video ends; and outputting object detection results, wherein; the fast object detection method is integrated with a LED lighting device; a model for an object with n parts is formally defined by (n+2)-tuple (F0, P1 , . . . , Pn, b), wherein F0 is a root filter, Pi is a model for a i-th part and b is a real-valued bias term, n being an integer; and provided that a location of each filter in a feature pyramid is (p0 , . . . , pn), and pi=(xi, yi, li) specifies a level and position of the i-th filter, a score of a window is defined by; - View Dependent Claims (2, 3, 4)
-
-
5. A fast object detection system based on a deformable part model (DPM), comprising:
-
a camera configured to capture a video; a receiving module configured to receive an image frame from a plurality of frames in the video captured by the camera; an objectness measure module configured to identify candidate regions in the image frame that may contain at least one object via the objectness measure based on Binarized Normed Gradients (BING), the candidate regions being a subpart of the received image frame, wherein the objectness measure quantifies how likely it is for a region in the image frame to contain an object as opposed to backgrounds; a Histogram of Oriented Gradients (HOG) module configured to calculate a HOG feature pyramid of the image frame; a DPM detection module configured to perform DPM detection for the identified candidate regions that may contain the at least one object based on the calculated HOG feature pyramid; and a label module configured to label the at least one detected object using at least one rectangle box via non-maximum suppression (NMS), wherein; the fast object detection system is integrated with a LED lighting device; a model for an object with n parts is formally defined by (n+2)-tuple (F0, P1 , . . . , Pn, b), wherein F0 is a root filter, Pi is a model for a i-th part and b is a real-valued bias term, n being an integer; and provided that a location of each filter in a feature pyramid is (p0 , . . . , pn), and pi=(xi, yi, li) specifies a level and position of the i-th filter, a score of a window is defined by; - View Dependent Claims (6, 7, 8, 9)
-
Specification