US 11,379,719 B2Granted

Method and system for tracking an object

AssigneeFotoNation Limited

InventorsDragos Dinu, Mihai Constantin Munteanu, Alexandru Caliman

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method of tracking an object across a stream of images comprises determining a region of interest (ROI) bounding the object in an initial frame of an image stream. A HOG map is provided for the ROI by: dividing the ROI into an array of M×N cells, each cell comprising a plurality of image pixels; and determining a HOG for each of the cells. The HOG map is stored as indicative of the features of the object. Subsequent frames are acquired from the stream of images. The frames are scanned ROI by ROI to identify a candidate ROI having a HOG map best matching the stored HOG map features. If the match meets a threshold, the stored HOG map indicative of the features of the object is updated according to the HOG map for the best matching candidate ROI.

Claims20

Dependent claims

A method of tracking an object across a set of image frames, the method comprising:

inputting a first frame of the set of image frames into a first neural network, the first neural network comprising at least one convolutional layer;
receiving a first output from the first neural network representative of a first map value associated with the first frame;
inputting the first output into a second neural network, the second neural network comprising at least one fully-connected layer;
receiving a second output from the second neural network representative of a region of interest in the first frame that comprises the object;
determining a weight value based at least in part on the first map value and the region of interest;
inputting a second frame of the set of image frames into the first neural network;
receiving a third output from the first neural network representative of a second map value associated with the second frame;
inputting the second map value and the weight value into a third neural network;
receiving a fourth output from the third neural network identifying a region of interest in the second frame as matching the region of interest in the first frame;
and
determining a location of the object in the second frame based at least in part on the fourth output.

8 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/746,430Filed 17 Jan 2020 · continuation
Priority: 13 Jun 2016
Published: US 2020/0226469 A116 Jul 2020
Granted: 5 Jul 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification19 codes

G06V 20/52
Context or environment of the image: surveillance or monitoring of activities, e.g. for recognising suspicious objects
G06F 18/2413
Relating to the classification model, e.g. parametric or non-parametric approaches: based on distances to training or reference patterns
G06N 3/0495
Architecture, e.g. interconnection topology: quantised networks; Sparse networks; Compressed networks
G06N 3/0499
Architecture, e.g. interconnection topology: feedforward networks

Family

PCT/EP2016/063446Parent of this continuation-in-part · filed 13 Jun 2016
Application15/426,413Parent of this division · filed 7 Feb 2017
Application16/532,059Parent of this continuation · filed 5 Aug 2019
US 10,373,052 B2Parent of this division · filed 6 Aug 2019
US 2020/0226469 A1Pre-grant publication · published 16 Jul 2020
US 10,540,586 B2Parent of this continuation
Application16/532,059Parent of this division
Application15/426,413Parent of this continuation-in-part
US 2017/0358086 A1Published application
US 2019/0354864 A1Published application
US 11,379,719 B2This patent

From the US filing history. Foreign family members aren’t listed.