Huawei officially released the good hope cloud service to attack the field of machine vision

Machine vision is a rapidly developing branch of artificial intelligence. Simply put, machine vision is to use machines instead of human eyes to make measurements and judgments. The machine vision system converts the captured target into an image signal through a machine vision product (ie, image capture device, divided into CMOS and CCD), and transmits it to a dedicated image processing system to obtain the morphological information of the captured target. Information such as brightness and color are converted into digital signals; the image system performs various operations on these signals to extract the characteristics of the target, and then controls the on-site equipment actions according to the results of the discrimination. Machine vision is a comprehensive technology, including image processing, mechanical engineering technology, control, electric light source lighting, optical imaging, sensors, analog and digital video technology, computer software and hardware technology (image enhancement and analysis algorithms, image cards, I/O card, etc.). A typical machine vision application system includes image capture, light source system, image digitization module, digital image processing module, intelligent judgment decision module and mechanical control execution module. The most basic feature of the machine vision system is to improve the flexibility and automation of production. In some dangerous working environments that are not suitable for manual operation or occasions where artificial vision is difficult to meet the requirements, machine vision is often used to replace artificial vision. At the same time, in the process of large-scale repetitive industrial production, the use of machine vision inspection methods can greatly improve the efficiency and automation of production. Today, China is becoming one of the most active regions in the world for the development of machine vision, with applications covering various industries of the national economy such as industry, agriculture, medicine, military, aerospace, meteorology, astronomy, public security, transportation, security, and scientific research. The important reason is that China has become the processing center of the global manufacturing industry. The high-demand parts processing and corresponding advanced production lines have brought many machine vision systems and application experience with international advanced levels into China. Recently, Huawei Machine Vision launched the Good Hope cloud service, and signed cooperation agreements with 18 start-up partners including iSoftStone, Yuncong Technology, and Nanjing Aokan. The release of Good Hope Cloud, an industry video cloud service, signifies that the solution architecture for machine vision end-cloud collaboration centered on Good Hope Cloud service is officially complete. It is reported that the Good Hope development platform is a minimalist intelligent algorithm development platform for end users and developers of Huawei Machine Vision. Based on the underlying capabilities of Huawei Cloud ModelArts, it provides“dev-train-deploy-inference”One-stop service. , the Good Hope development platform provides 9 categories of visual pre-training models, which can reduce the model that originally required 100,000-level data training to 1,000-level data. Among them, single action recognition, continuous action recognition, complex behavior recognition, etc. are the first in the industry, and can realize more complex intelligent functions. The intelligent labeling in the semi-manual mode of the Good Hope development platform only requires five steps of uploading data, a small amount of manual labeling, generating an initial model, massive self-labeling, and manual proofreading, which saves 50% to 80% of data labeling labor. A normal pig face recognition model may reach 20M, but it can become 20M after distillation and pruning on the good hope development platform, and the inference speed is increased from 630ms to 40ms. Duan Aiguo said that this was due to Huawei's deep understanding of the GPU/NPU chip architecture to achieve automatic model optimization. Since Huawei officially entered the field of intelligent security in 2019, Huawei machine vision“good hope”The integrated architecture of device-edge-cloud collaboration is increasingly taking shape. At the same time, Huawei's machine vision has also established an open ecosystem with many partners in the fields of algorithms, security, and channels, focusing on several core application scenarios. Huawei Machine Vision has finally begun to sell cloud to the distribution market, which means that the ground-launch of Huawei's security products in 2020 should be relatively optimistic. Huawei is confident that terminal products can drive cloud service sales. At the same time, cloud services will also be used for Huawei Machine Vision. AI technology output provides better support.