NEC Develops High-speed and High-precision Object Detection Acceleration Technology for Edge Equipment
- Approximately 8 times faster processing speed for car license plate detection -
TOKYO, Dec 01, 2021 - (JCN Newswire) - NEC Corporation (TSE: 6701) today announced the development of a "gradual deep learning-based object detection technology" that enables efficient and high throughput object detection for video analytics while maintaining detection accuracy.
This technology enables up to eight times the processing speed of object detection for large volumes of images, even on edge devices with limited processing capacity.
NEC aims to commercialize this technology in fiscal 2022, following further research and development.
Video analytics are expected to be utilized for a wide range of applications, such as analyzing camera images of vehicles at intersections, optimizing traffic control, and analyzing camera images of stores and warehouses to detect intrusion or to optimize facility management.
To perform these video analytics in real time, it is ideal to process them on an edge device near a sensor, such as a camera.
However, because cooling is difficult to manage and electricity consumption is restricted in edge devices, high-performance processors such as GPUs used in high-performance servers are not available, and processing capacity is constrained.
In video analytics, object detection software that utilizes deep learning (hereinafter "object detection AI model") performs object detection processing in order to find the object to be analyzed from images captured by a camera
Since highly accurate object detection AI models have a large amount of operations though, it is difficult for edge devices to process a large amount of images due to constraints on processing capacity. If the amount of operations for a high-speed object detection AI model is reduced, for example, the accuracy declines and the recognition accuracy requirements for image analysis cannot be met.
Application of NEC's newly developed gradual deep learning-based object detection technology enables efficient, high-speed, and high-precision detection of subjects from a large amount of images, even in an edge device with limited processing capacity, and enables simultaneous processing of images from multiple cameras in real time.
Technology Features
1. High-speed, high-precision detection at the same time
This technology combines an object detection AI model that is high-speed, but is only roughly accurate, with another object detection AI model that is highly accurate, but computationally complex. This combination enables efficient processing of multiple images and results in high-speed, high-precision detection.
First, a high-speed object detection AI model detects multiple objects quickly, but with rough accuracy, then the detected results are processed together with a high-precision object detection AI model to gradually refine the detected objects.
As a result, in an example of detecting a car license plate from a camera image, processing speed was approximately eight times faster than when using an object detection AI model with high accuracy alone, while maintaining detection accuracy*.
2. Compatible with various detection targets, detection methods, and AI chips
This technology is compatible with a diverse range of object detection processes according to detection targets, such as people, vehicles and car license plates, without being limited to specific detection targets and specific processing methods.
In addition, the technology's application is not limited to a specific AI chip. By taking advantage of the fact that AI chips have a large number of computing resources in common, the technology makes effective use of the internal computing power of chips.
Going forward, NEC aims to enhance the safety, security, and convenience of society by expanding the use of video analytics technologies to a wide variety of applications.
*Speed varies depending on the device used, the type of detection engine and the quality of image data.
About NEC Corporation
NEC Corporation has established itself as a leader in the integration of IT and network technologies while promoting the brand statement of "Orchestrating a brighter world." NEC enables businesses and communities to adapt to rapid changes taking place in both society and the market as it provides for the social values of safety, security, fairness and efficiency to promote a more sustainable world where everyone has the chance to reach their full potential. For more information, visit NEC at https://www.nec.com.
Source: NEC Corporation Sectors: CyberSecurity, Artificial Intel [AI]
Copyright ©2025 JCN Newswire. All rights reserved. A division of Japan Corporate News Network.
|
Latest Release
 Mitsubishi Motors Launches the All-New Grandis for the European Market Jul 02, 2025 12:10 JST
|  Valuufy partners with Mainichi Future Creation Lab, Supporting New Approaches to Business Sustainability Jul 02, 2025 12:00 JST
|  Fujitsu launches solution to enhance customers' global supply chain resilience Jul 02, 2025 11:32 JST
|  MHI Receives Order to Supply Four Circulating Water Pumps for Units 5 and 6 of Sanmen Nuclear Power Plant in China Under Collaboration with Dongfang Electric Machinery Jul 02, 2025 11:30 JST
|  Multi-purpose Arena in Odaiba Aomi Area TOYOTA ARENA TOKYO Construction Completed Jul 01, 2025 22:56 JST
|  1Finity, a Fujitsu company, commences operations and reveals brand identity Jul 01, 2025 22:53 JST
|  MHI Thermal Systems Begins Field Test of Jointly Developed "Surplus Renewable Energy Absorption and Release System" Jul 01, 2025 22:40 JST
|  Japan's Telecommunications Carriers Strengthen Disaster Response Through Collaborative Information Sharing Jul 01, 2025 22:30 JST
|  JCB and Mandai Wildlife Group Deepen Partnership with exclusive discounts for JCB cardmembers Jul 01, 2025 16:00 JST
|  Fujitsu provides Japan's first AI-powered cloud-based library search service Jul 01, 2025 11:30 JST
|  JCB Brings Apple Pay to Cardmembers in Vietnam Jul 01, 2025 11:15 JST
|  First Shipment of LNG from the LNG Canada Project Jul 01, 2025 11:00 JST
|  Approval in Principle (AiP) for World's First LCO2 / Methanol Carrier Jun 30, 2025 20:30 JST
|  Acropolis Rally Greece: Day 4 Sunday success and second overall for TOYOTA GAZOO Racing's Ogier Jun 30, 2025 20:15 JST
|  Mitsubishi Fuso-Hino Merger: 4 Firms Collaborate for the Future of Commercial Vehicles Jun 30, 2025 20:10 JST
|  Six Companies Establish BlueRebirth Council to Expand Use of Recycled Materials in New Vehicles Jun 30, 2025 19:25 JST
|  Honda Changes Plan to Build New Production Plant for Next-generation Fuel Cell Module in Japan Jun 30, 2025 19:20 JST
|  MHI-AC&R Receives Recommendation Award of JARAC's 42nd Excellent Energy Saving Equipment Awards Jun 30, 2025 19:00 JST
|  The University of Osaka and Fujitsu Japan launch joint research on AI-powered education support for culturally and linguistically diverse children in Japan Jun 30, 2025 12:00 JST
|  JCB has launched contactless subway payment services in Shanghai and Beijing, marking the first such service in mainland China Jun 30, 2025 12:00 JST
|
More Latest Release >>
|