Inanyou Show

Contact Us


News & Notice   /   Q&A   /   Reference Document   /   Product Inquiry

Home > CS Center > News & Notice

News & Notice

Rockchip released the deep learning-based target detection solution, speeding up the comme simon.jeon 2018-05-24

Rockchip released the deep learning-based target detection solution, speeding up the commercial process of high-end AI




On May 16, 2018, Rockchip released the deep learning-based target detection solution powered by RK3399. It can provide Turnkey solutions for high-end AI industry and support both Android and Linux with a target detection speed of more than 8 frames per second.

Target detection is a very popular research orientation in AI field. It involves the positioning and classification of target objects in pictures or videos. It is quite difficult for machines to acquire the abstract concept of objects and position them from RGB pixel matrix, which poses great challenges to the application of AI.

Currently, the major R&D orientations of AI technology includes: face detection, body detection, vehicle detection, QR code detection and gesture detection, which can be widely used in monitoring, intelligent transportation, new retails, natural interactions, etc., while the target detection technology is the basis of these applications. The deep learning-based target detection technology is highly accurate and robust, and yet cannot be actually deployed and applied in embedded devices for a long time due to heavy computation.

Tailored to AI market and technical demands, Rockchip conducts specific optimization on MobileNet SSD network based on high-performance RK3399 platform. As a result, the running frame rate of the high-precision MobileNet SSD300 1.0 reaches over 8, while that of the MobileNet SSD300 0.75 with slightly lower precision and faster speed reaches over 11. The quasi real-time running speed brings the target detection AI technology from embedded terminals to practical applications.



Apart from the quasi real-time running speed, the solution supports the TensorFlow Lite model exported from the Google TensorFlow Object Detection training. As of now, there have been a substantial number of application cases based on TensorFlow Object Detection, covering different types of detections, from face to object, making it one of the most convenient and prevalent target detection frames in the industry.

Rockchip deep learning target detection solution, based on RK3399, supports both Android and Linux, and improves the user experience in using AI products of target detection technology. The solution substantially shortens the R&D cycle and facilitates the earlier launch of more high-end AI products.




Upgraded to Android 8.1! Rockchip High Cost-effective Tablet Solutions Showed during HK El simon.jeon 2018-05-23
A thousand developers join the Rockchip Developer Conference simon.jeon 2018-04-30
Powered by Rockchip OP1-RK3399, Google released world’s first Chrome OS Chromebook Tab 10 simon.jeon 2018-04-30
Pulierde Linux Smart Cast A3 Officially Launched! Powered by Rockchip RK3036 simon.jeon 2018-04-30
Powered by RK3229 , Phicomm AI Speaker R1 Released simon.jeon 2018-03-21
Rockchip has participated 2018 embedded world Exhibition & Conference in Germany simon.jeon 2018-03-21
Sogou Travel Translator is officially released, AI-powered by RK3399! simon.jeon 2018-03-21
The Next ODROID by Hardkernel. simon.jeon 2018-02-12
CES2018 Rockchip announces Android Things™ Turnkey SOM 서학진(hj.seo) 2018-01-11
Rockchip Released Its First AI Processor RK3399Pro NPU Performance up to 2.4TOPs 서학진(hj.seo) 2018-01-08
New upgrade of RV1108 face recognitionsolution, speeding up AI era 서학진(hj.seo) 2018-01-08
Upgraded Rockchip RK3328 UHD TV BOX Solution at Three Times the Speed 서학진(hj.seo) 2017-10-25
Fully Support Google Assistant! Rockchip RK3229 Solution Released at Google I/O Conference 디렉터(director) 2017-08-02
Applications of RV1108 solution| Dual-eye 360 degree 3K panoramic video camera solution on 디렉터(director) 2017-08-02