公开(公告)号：US20240153106A1

公开(公告)日：2024-05-09

申请号：US18549399

申请日：2022-03-07

Applicant: HITACHI ASTEMO, LTD.

Inventor： So SASATANI ,  Goshi SASAKI ,  Trongmun JIRALERSPONG

IPC: G06T7/246 ,  G06V10/25

CPC classification number: G06T7/246 ,  G06V10/25 ,  G06T2207/20076 ,  G06T2207/30241 ,  G06T2207/30252 ,  G06V2201/07

Abstract: An object of the present invention is to generate a highly accurate trail by correcting detection box information of an object in an object tracking apparatus that generates a trail of an object within a measurement range. According to the present invention, there is provided an object tracking apparatus (100) that generates a trail of an object within a measurement range of a camera (2), the object tracking apparatus (100) including: an object detecting unit (4) that detects an object for each of a plurality of frames acquired by a sensor; a detection box reliability calculating unit (8) that calculates a reliability of a detection box based on flow information between frames of the detection box in which the object has been detected; a detection box position correcting unit (9) that corrects detection box information of a low-reliability detection box, using detection box information of a high-reliability detection box; and a trail generating unit (10) that generates a trail of an object, using the corrected detection box information.

公开(公告)号：US20240127567A1

公开(公告)日：2024-04-18

申请号：US18547762

申请日：2022-02-25

Applicant: HITACHI ASTEMO, LTD.

Inventor： Goshi SASAKI ,  So SASATANI

IPC: G06V10/22 ,  G06T7/246 ,  G06T7/73 ,  G06V20/58

CPC classification number: G06V10/22 ,  G06T7/246 ,  G06T7/73 ,  G06V20/58 ,  G06T2207/10016 ,  G06T2207/30252

Abstract: Provided are a detection frame position accuracy improvement system and a detection frame position correction method capable of estimating a detection frame position with high accuracy using information before and after a target frame. The detection frame position accuracy improvement system includes a time-series image input unit 10 that inputs time-series images, an object detection unit 20 that detects a target object with the time-series images, a detection frame position distribution estimation unit 30 that estimates a distribution of detection frame position coordinates at time t from detection results of the target object up to time t−1 (t is a positive integer), a detection frame prediction unit 40 that predicts positions of a detection frame at times t+1 to t+n (n is a positive integer) according to the detection results and the distribution, a detection frame uncertainty estimation unit 50 that updates the distribution of the detection frame position coordinates at time t according to degrees of overlap between the detection results of the target object at the times t+1 to t+n and the predicted detection frame and estimates uncertainty of a detection frame at time t, and a detection frame correction unit 60 that corrects the detection frame at time t on the basis of the detection frame and the uncertainty.

公开(公告)号：US20230196847A1

公开(公告)日：2023-06-22

申请号：US17925586

申请日：2021-02-24

Applicant: Hitachi Astemo, Ltd.

Inventor： Kyoko ISHIDA ,  Goshi SASAKI ,  So SASATANI

IPC: G07C5/00 ,  G06V20/58 ,  G06T7/50 ,  G06T7/70 ,  G06T7/20 ,  B60W40/04 ,  G08G1/16

CPC classification number: G07C5/008 ,  G06V20/58 ,  G06T7/50 ,  G06T7/70 ,  G06T7/20 ,  B60W40/04 ,  G08G1/166 ,  G06T2207/30261 ,  B60W2554/80

Abstract: An object of the present invention is to provide a technique for suppressing a data capacity by appropriately selecting a data item that needs to be collected in order to analyze an accident situation or the like. An in-vehicle device according to the present invention acquires data describing a state of a vehicle and a surrounding situation of the vehicle, and selects and outputs a record in which at least one of an operation of the vehicle or an operation of a surrounding object exceeds a threshold among records described in the data (see FIG. 1).