Cybercore and SC Automotive Engineering signed a strategic business alliance agreement on customer development and technology development.

Cybercore Co., Ltd., a developer of image recognition AI algorithms (hereinafter referred to as “Cybercore”; Head Office: Morioka City, Iwate Prefecture; President: Hiroshi Abe), and SC Automotive Engineering, Co., Ltd. (“SCAE”; Head Office: Chiyoda-ku, Tokyo; President and CEO: Toshimi Yamanoi), a wholly owned subsidiary of Sumitomo Corporation that provides technology to major automotive companies, have signed a strategic business alliance agreement to provide solutions that utilize Cybercore’s world-leading* image recognition algorithms to customers of SCAE and SCAE’s parent company, Sumitomo Corporation.

SCAE provides a variety of solutions to major automakers and other transportation equipment manufacturers, and this business alliance is expected to leverage Cybercore’s core technologies, including the LuxEye® image sharpening library, the NeuroEye® lightweight AI algorithm, the WipeEye® missing image restoration algorithm Cybercore’s core technologies, and the DetectEye™ AI for judging abnormal products without the need for defective product learning, are expected to be leveraged to help solve customer issues using cutting-edge technologies.

Cybercore has been active in international AI competitions, where few Japanese companies have been successful. In addition, in April this year, the company launched a new AI system for vehicles. In April of this year, the ReID algorithm was ranked number one in the world by the international algorithm evaluation site Papers with Code. In June of this year, they won the YouTube-VOS 2021 Challenge, an international competition for image AI, out of 331 entries, and gave two presentations at the aforementioned CVPR 2021 conference.

In addition to automated driving, we have experience in developing solutions in a wide range of fields, including infrastructure, factory automation (FA), medical and welfare, and retail, such as convenience stores, as well as the RushEye® AI system for measuring congestion rates using depth cameras, which has already been introduced in the Tokyo Metro. We have a track record of developing solutions in a wide range of fields.

SCAE and the Sumitomo Corporation Group will reinforce Cybercore’s strengths in technology and its weaknesses in commercialization and sales expansion and will promote the business alliance with a view to a possible capital alliance in the future. With this opportunity, we expect to further accelerate our efforts to provide society with intrinsically valuable technologies.


SCオートモーティブエンジニアリング様と、 顧客開拓や技術開発についての戦略的な業務提携合意書を締結しました。


画像認識AIアルゴリズム開発を手掛ける株式会社サイバーコア(以下「サイバーコア」、本社:岩手県盛岡市、代表取締役社長:阿部英志)と、住友商事の100%子会社で自動車大手への技術提供等を行なうSCオートモーティブエンジニアリング株式会社(以下「SCAE」、本社:東京都千代田区、代表取締役社長:山ノ井 利美)はこのたび、サイバーコアのもつ世界でもトップクラス*の画像認識関連アルゴリズムを活用したソリューションをSCAEおよびSCAEの親会社にあたる住友商事の顧客に提供することを目的とした戦略的な業務提携合意書を締結しました。


サイバーコアはこれまで、日本企業ではほとんど成果が出ていなかった国際的なAIコンペティションで活躍。2018年に権威ある国際AIコンペティション&カンファレンス「CVPR 2018」の「iMaterialist」カテゴリーで2,261エントリー中準優勝の成績を収めました。また、今年4月には車両再識別(ReID)アルゴリズムが国際的なアルゴリズム評価サイト「Papers with Code」のランキングで世界1位を記録。続いて今年6月には画像AIの国際コンペティション「YouTube-VOS 2021 Challenge」で331エントリー中優勝を飾り、前述のカンファレンス「CVPR 2021」で2本のプレゼンテーションを実施するなど、高い技術力を有しています。





画像認識AI アルゴリズム開発のサイバーコア、不良品学習が不要の 正例判定AI アルゴリズム「DetectEye™」をリリース。エッジバージョンも開発へ。

04_20211208_DetectEye_PressRelease vF_link1



詳しくは、DetectEye Web Application操作マニュアルに記載されております。

DetectEye Web Application操作マニュアル


Cybercore’s train congestion measuring AI system has been broadcasted on NHK WORLD worldwide.

Cybercore’s train congestion measuring AI system developed with Tokyo Metro has been broadcasted on NHK WORLD worldwide with English subtitles. The program was featured on NHK nationwide in Japan in July.

Please watch the story and the movie, so you will understand Cybercore’s vision and culture at a glance.


サイバーコアの列車混雑計測システムが「NHK WORLD」で世界へ向けて放映されました。

先日NHK「おはよう日本」で国内放映された、東京メトロと共同開発した列車混雑計測システムに関して、「NHK WORLD」を通じて世界へサイバーコアの技術が紹介されました。



Cybercore’s train congestion measuring AI system was featured on NHK “Ohayo Nippon”.

Cybercore was featured on NHK (national broadcasting station) for our train congestion measuring AI system this morning. The system was developed collaborating with Tokyo Metro and we have applied patent in March as announced previously.

Please watch the story and the movie, so you will understand Cybercore’s vision and culture at a glance.

Please see NHK website for the article and movie:
Story (Japanese Only)
Movie (Japanese Only)

Update (Aug 30, 2021):
Featured in “Local Digital Transformation (DX)” on NHK WEB:

Read the Story (Japanese Only)





NHK おはよう日本 AI画像解析で混雑情報 地方ベンチャーの底力

NHK ビジネス特集「なぜ地方でできる?コロナ禍のDX」へ掲載されました




Cybercore R&D team won 1st place in YouTube-VOS 2021 Challenge. The team will make 2 presentations during CVPR 2021, a prestigious Image AI conference.

Researchers from Cybercore Co., Ltd. (Morioka, Iwate) have won the 1st place among 331 entrants and 39 finalists in the international computer vision competition YouTube-VOS 2021 Challenge. The team will have a presentation at one of the most prestigious computer vision conferences CVPR 2021 on June 20th.

Besides the achievement in the YouTube-VOS 2021 Challenge, as previously announced in May, Cybercore team has also won the 1strank in Vehicle Re-Identification in Papers with Code. This algorithm was developed during the AI City Challenge competition The team will present their solution at the CVPR 2021’s AI City Challenge section in June as well.


Overview of YouTube-VOS 2021 Challenge

YouTube-VOS 2021 Challenge has 3 different competitions, and we joined the Video Instance Segmentation one. Our team participated the challenge with 4 researchers from Cybercore’s Ho Chi Minh R&D center.

Video Instance Segmentation is a multi-task problem, which performs three tasks simultaneously, including detection, segmentation, and tracking. Our approach takes the advantage of data efficiency analysis, multi-task learning, and deep-supervision. This not only improves the model’s speed and memory, while yields higher accuracy and reduces training time thanks to the joined optimization framework.

Our solution has a wide range of applications, such as video understanding, object detection and tracking for autonomous driving, human behavior, or motion analysis. Taking the video understanding problem as an example, our solution can segment any objects (person, vehicles, animals) in the videos and track them for specific purposes. Segmented results can serve as another source for action analysis, such as in sport, e.g., supporting coaches with more information to train their teams. In autonomous driving applications, our solution can segment moving objects on the streets, such as pedestrians, riders, other vehicles, or traffic signs. This helps autonomous vehicles be able to take appropriate action on the ride.


CVPR 2021 workshop

YouTube-VOS Challenge Outline and Results




サイバーコア、画像AIの国際コンペ 「YouTube-VOS 2021 Challenge」で331エントリー中1位に。権威ある国際カンファレンス「CVPR 2021」で2本のプレゼンテーションを実施へ。

株式会社サイバーコア(本社:岩手県盛岡市、代表取締役社長:阿部英志)の技術開発チームは、5月におこなわれたコンピュータビジョンの国際コンペティション「YouTube-VOS 2021 Challenge」において、331エントリー・39ファイナリスト中の1位に輝きました。同チームはその成果をうけ、国際的に権威あるコンピュータビジョンのカンファレンスである「CVPR 2021」内で、6月20日にプレゼンテーションを行う予定です。

また、「YouTube-VOS 2021 Challenge」に先駆けて既報のとおり、サイバーコアチームは国際的なアルゴリズム評価サイト「Papers with Code」の車両再認識(Vehicle Re-Identification)カテゴリでも5月時点でNo.1にランキングされています。このアルゴリズムは別のコンペティション「AI City Challenge」に向けて開発したものですが(サイバーコアは同コンペティションでは9位の結果)、この車両再認識アルゴリズムについても「CVPR 2021」の「AI City Challenge」セクション内でプレゼンテーションを行う予定です。


■ YouTube-VOS 2021 Challenge コンペティション概要

 「YouTube-VOS 2021 Challenge」はさらに3つのコンペティションに細分化されていますが、サイバーコアチームはそのうち「Video Instance Segmentation (VIS)」のカテゴリにエントリーしました。サイバーコアのホーチミンR&D拠点から4名の研究者がチームを編成し、コンペティションに挑みました。





CVPR 2021 workshop

YouTube-VOS Challenge Outline and Results