Sighthound Launches Vehicle Recognition in the Cloud
Sighthound Cloud now able to identify make, model and color of vehicles
Palo Alto, California - December 12, 2016 - Sighthound, Inc. today announced the release of a new vehicle detection and recognition engine for its Sighthound Cloud API service. The vehicle recognizer is able to analyze an image and return the make, model, and color of the vehicle using its proprietary deeply learned computer vision algorithms. The vehicle recognizer complements an existing set of APIs that are currently available to developers through the Sighthound Cloud service including person, face, gender, age, and facial landmark detectors as well as the industry's leading facial recognition API.
Sighthound is a pioneer in the world of computer vision and artificial intelligence. Founded in 2012, Sighthound's Computer Vision Research Lab designs and builds powerful proprietary deep networks that outperform leading academic and industry competitors.
"As the market has become more aware of Sighthound's experience in artificial intelligence, we receive a lot of requests for customizing our deep learning networks to specific purposes," said Stephen Neish, Sighthound's CEO. "It became clear that our vehicle recognizer was better than anything else on the market and it has generated a lot of interest among law enforcement and public safety agencies. We're happy now to make this capability generally available to the developer community."
The latest addition to the suite of Sighthound Cloud APIs, the vehicle recognizer knows over 800 vehicle models. The recognizer is commercially available starting today, and will detect vehicles in images and return a result indicating make, model, color, and the confidence levels associated with the result in around a second. Historically, vehicle recognition has been constrained by the requirement that images be submitted from specific viewpoints. However, Sighthound's vehicle recognizer has been trained to accept images from differing angles and distances. The vehicle recognizer includes most North American passenger vehicle models built after 1989, and is accurate to over 95% on a standardized blind test set of 75,000 images.
Alongside the developer API, Sighthound released a demonstration version of the vehicle recognition engine on its website.
Sighthound makes it easy for developers to get started by offering free tutorials, sample code, and documentation to help integrate APIs into applications. Developers can sign up for the Sighthound Cloud API service and place up to 5,000 API calls free of charge at https://www.sighthound.com/products/cloud. Paid accounts (Basic, PRO, and Enterprise) have access to production servers for commercial use and begin at $49 per month.
Sighthound's new vehicle recognition engine joins an expanding range of products that use Sighthound's state-of-the-art computer vision algorithms. Sighthound also markets Sighthound Sentry, the computer vision engine used by OEMs to add intelligence to their products and services, and Sighthound Video, artificial intelligence security software for homes and businesses.
Sighthound makes sense of movement through our world. By building state-of-the-art computer vision research into easy-to-use software, Sighthound makes it easy for computers to see.