-
公开(公告)号:US20220277553A1
公开(公告)日:2022-09-01
申请号:US17624913
申请日:2019-07-11
Applicant: NEC Corporation
Inventor: Katsuhiko TAKAHASHI , Yuichi NAKATANI , Asuka ISHII , Tetsuo INOSHITA , Gaku NAKANO
IPC: G06V10/776 , G06V10/22 , G06V10/774
Abstract: In an object detection device, a plurality of object detection units output a score indicating probability that a predetermined object exists, for each partial region set to image data inputted. The weight computation unit computes weights for merging the scores outputted by the plurality of object detection units, using weight calculation parameters, based on the image data. The merging unit merges the scores outputted by the plurality of object detection units, for each partial region, with the weights computed by the weight computation unit. The target model object detection unit configured to output a score indicating probability that the predetermined object exists, for each partial region set to the image data. The first loss computation unit computes a first loss indicating a difference of the score of the target model object detection unit from a ground truth label of the image data and the score merged by the merging unit. The first parameter correction unit corrects parameters of the target model object detection unit to reduce the first loss.
-
32.
公开(公告)号:US20220254136A1
公开(公告)日:2022-08-11
申请号:US17587065
申请日:2022-01-28
Applicant: NEC Corporation
Inventor: Tomokazu KANEKO , Katsuhiko TAKAHASHI , Makoto TERAO , Soma SHIRAISHI , Takami SATO , Yu NABETO , Ryosuke SAKAI
Abstract: An image acquisition unit 110 acquires a plurality of images. The plurality of images include an object to be inferred. An image cut-out unit 120 cuts out an object region including the object from each of the plurality of images acquired by the image acquisition unit 110. An importance generation unit 130 generates importance information by processing the object region cut out by the image cut-out unit 120. The importance information indicates the importance of the object region when an object inference model is generated, and is generated for each object region, that is, for each image acquired by the image acquisition unit 110. A learning data generation unit 140 stores a plurality of object regions cut out by the image cut-out unit 120 and a plurality of pieces of importance information generated by the importance generation unit 130 in a learning data storage unit 150 as at least a part of the learning data.
-
公开(公告)号:US20210201007A1
公开(公告)日:2021-07-01
申请号:US17058796
申请日:2018-05-29
Applicant: NEC Corporation
Inventor: Takashi SHIBATA , Azusa SAWADA , Katsuhiko TAKAHASHI
Abstract: The purpose of the present invention is to detect an object in images accurately by means of image recognition without using a special device for removing the influence of the parallax between a plurality of images. An image transformation unit (401) transforms a plurality of images acquired by an image acquisition unit (407). A reliability level calculation unit (402) calculates a level of reliability representing how small the misalignment between images is. A score calculation unit (405) calculates a total score taking into account both an object detection score based on a feature quantity calculated by a feature extraction unit (404), and the level of reliability calculated by the reliability level calculation unit (402). An object detection unit (406) detects an object in the images on the basis of the total score.
-
公开(公告)号:US20190253618A1
公开(公告)日:2019-08-15
申请号:US16395352
申请日:2019-04-26
Applicant: NEC CORPORATION
Inventor: Ryoma OAMI , Katsuhiko TAKAHASHI , Yuusuke KONISHI , Hiroshi YAMADA , Hiroo IKEDA , Junko NAKAGAWA , Kosuke YOSHIMI , Ryo KAWAI , Takuya OGAWA
CPC classification number: H04N5/23222 , H04N5/23219 , H04N7/181
Abstract: An information processing apparatus (2000) includes a determination unit (2020) and a notification unit (2040). The determination unit (2020) determines whether a field of view of a second camera is correct, on the basis of a first captured image (40), a second captured image (50), and relationship information (information indicating the relationship to be satisfied between a field of view of a first camera and the field of view of the second camera). In a case in which the field of view of the second camera is not correct, the notification unit (2040) notifies that the field of view of the second camera is not correct. The first camera is provided in a head-mounted display worn by a person. The second camera is provided in a part other than the head-mounted display.
-
公开(公告)号:US20190215494A1
公开(公告)日:2019-07-11
申请号:US16352340
申请日:2019-03-13
Applicant: NEC CORPORATION
Inventor: Ryoma OAMI , Katsuhiko TAKAHASHI , Yuusuke KONISHI , Hiroo IKEDA , Junko NAKAGAWA , Kosuke YOSHIMI , Yukie EBIYAMA , Ryo KAWAI , Takuya OGAWA
CPC classification number: H04N7/185 , G06K9/00288 , H04N5/23206
Abstract: A surveillance system (1) includes an area information acquisition unit (101), a request information provision unit (102), and a participation consent reception unit (103). The area information acquisition unit (101) acquires information of a surveillance-desired area. The request information provision unit (102) provides participation request information for surveillance that is conducted by using an image capturing unit of a portable terminal in the surveillance-desired area. The participation consent reception unit (103) receives participation consent as a response to the participation request information, from the portable terminal.
-
-
-
-