Leopard Imaging

Leopard Imaging

Leopard Imaging Inc. provides high definition embedded camera modules, cameras, and related products that enable customers to develop products for the consumer, industrial, automotive, scientific, and medical industries.  Leopard can support the entire design cycle from prototype to production even for small-to-medium volumes.

Customers can choose from camera modules; box, stereo, and zoom cameras; and supporting interface, processing, and evaluation products.  Leopard designs with image sensors from Sony, Omnivision, and OnSemi, and provides products with a variety of interfaces such as USB, MIPI, or LVDS.

Get access to Leopard Imaging's talented engineers for manufacturing and design services, even for custom, small volume projects. Leverage Leopard Imaging's core knowledge in ISP tuning including:

  • 3A Algorithm (Auto Exposure, Auto White Balance and Auto Focusing)
  • Wide Dynamic Range (WDR)
  • Patented object location and AWB calibration

Thermal Imaging Solutions

Leopard Imaging Thermal Imaging Cameras come with state-of-the- art patent technology to provide real-time mass temperature, and mask detection quickly and accurately without contact. These cameras can be easily installed in various public environments such as airports, factories or office buildings. They are cost efficient, accurate, and easy to use.

Video

 

 

Leopard Imaging EdgeTuring™ leverages AWS services such as Amazon Kinesis Video Streams and Amazon Kinesis Data Streams (Amazon KDS) to create a seamless experience for customers to stream and analyze videos using a simple internet connection.
EdgeTuring™ has an accuracy ranging from 95% to 99% for several state of the art deep learning - based computer vision applications, such as object detection, image classification and others. It also processes frames much faster, supports more functions, consumes less power, and costs much less than any comparable solution—all with the ability to stream inputs in real time.

EdgeTuring™

EdgeTuring from Leopard Imaging

EdgeTuring™ —next-generation artificial intelligence processing solution for video analytics.

Leopard Imaging has been working to address the need for affordable multiprocessing power in deep learning applications. Using Socionext’s SC2000 image signal processor and the Hailo-8™ M.2 AI acceleration module, Leopard Imaging’s EdgeTuring™ consumes less power, performs at a higher level, and ensures greater reliability for video analytics and privacy at the edge than alternative solutions. Leveraging AWS services such as Amazon Kinesis Video Streams and Amazon Kinesis Data Streams (Amazon KDS), EdgeTuring™ creates a seamless experience for customers to stream and analyze videos using a simple internet connection.

EdgeTuring™ has an accuracy ranging from 95% to 99% for several state of the art deep learning - based computer vision applications, such as object detection, image classification and others. Additionally, it processes frames much faster, supports more functions, consumes less power, and costs much less than any comparable solution—all with the ability to stream inputs in real time.

Launched just last year, the Hailo-8™ AI M.2 module enables customers to integrate high performance AI capabilities of 26 Tera Operations Per Second (TOPS) into edge devices, providing a more flexible solution for accelerating a wide range of deep learning-based applications with high efficiency—optimizing time to market with a standard form factor. A comparison between the Hailo-8’s average Frames Per Second (FPS) with competitors across multiple standard NN benchmarks (based on the latest published figures) shows that Hailo’s AI modules achieve up to 26x higher FPS rate.

AWS provides coverage connected by high throughput, low latency, and highly redundant networking, which allows EdgeTuring™ to combine the advantages of both edge computing and cloud computing to achieve more functions in more applications.

EdgeTuring™ Product Features

 

Camera Specification
EdgeTuring™ Datasheet

 

 

Features
Image Processor: Socionext SC2000 Processor
Sony Diagonal 7.857 mm (Type 1/2.3)
CMOS Image Sensor IMX477
Resolution: 3840 (H) x 2160 (V)
Pixel Size: 1.55 x 1.55μm
Video Output: 4K @ 30 fps with EIS / 4K @ 15 fps with HDR
Color/Mono: Color
AI Module: Hailo-8™ M.2 Module
Multi-Sensor: Dual (Only one sensor works for AI)
Baseline: 40.70 mm
Lens: FOV 43.4° horizontal (each video)
Amazon AWS:
Amazon Kinesis Video Streams (KVS)
Amazon Kinesis Data Streams (KDS)
Operating Temp: 0 ℃ +60℃
Storage Temp: – 20 ℃ ~ +70℃
Weight: ~ 242 g
Size: 80.70 (L) x 38.00 (W) x 93.33 (D) mm
Part# LI-M10V-AI

 

 

Application
Industrial Automation
IoT
Smart Devices
Smart Retail

 

Time-of-Flight (ToF) Cameras

Leopard Imaging TOF Cameras

Leopard Imaging and Microsoft’s Azure Depth Platform program are working together to develop ToF cameras, aimed at democratizing cloud-connected 3D vision. In this collaboration, Leopard Imaging is developing 3D industrial cameras, which can securely connect with Azure Intelligent Edge and Intelligent Cloud platforms for a broad set of technologies and industry solutions.

Leopard Imaging will leverage Microsoft’s ToF technology with solutions in retail, physical security, healthcare, drones, IoT, robotics, and automotive industries—reinventing camera-imaging experiences for customers around the world.

Time of Flight Technology Overview

A ToF camera measures how long it takes for light to bounce off an object. Using this principle, the camera calculates the distance to all objects in a scene.
This point cloud data is used to compute and create a three-dimensional (3D) map of the object space. Thus, ToF cameras are also referred to as “depth cameras.”
Unlike stereo 3D methods, no image contrast is necessary, and ToF systems exhibit excellent mechanical robustness.

3D Stereo Cameras

Leopard Imaging 3D Stereo Cameras

Stereo vision is the technique of using two cameras, that are synchronized together to simulate human binocular vision, and create depth perception for machines. Binocular vision is how humans navigate around objects, and as such, is being employed in more and more arenas, as we learn to automate parts of our world.

The applications for stereo vision are increasing. Robots that move items around in a warehouse – whether storing or retrieving, need to be able to determine depth to navigate aisles and objects. Object manipulation also requires the ability to sense in 3D, to provide correct orientation and placement. Production lines are another place where sensing the 3D is becoming increasingly helpful and of course, robotics – creating a machine to interact and move as a human can, requires the ability to understand its environment. AI/VR, Home surveillance, 3D gesture control, medical cameras and research environments are all finding homes for new stereo vision applications.

Leopard Imaging has a growing range of stereovision camera modules to fit a variety of needs. With a horizontal field of view ranging from 50 degrees to 180 degree fisheye lenses and resolutions from VGA up to 3840 x 2160, Leopard range covers many different applications and price points.

Backed by a range of image processing engines, we can find a solution that fits your needs and processing requirements. Utilizing both rolling and global shutter sensors, we have solutions for slow and fast moving environments. There are color and mono sensor options depending on your requirements.

Many of the options are customizable, so talk to us about your stereo vision needs today, and we’ll work together to find the perfect solution.

 

Video

 

For more information: