Listen to this article
eCapture launches its first, branded, stereoscopic 3D depth sensing camera. Prior to the launch of this product, eCapture developed the camera internals and sold it as an OEM product to other camera manufacturers.
The company has also developed the technology for VR cameras and goggles and provided OEM components for two generations of the Oculas VR headset. eCapture has also developed VR and vision enhancement solutions for the military, all under OEM contracts.
The company is releasing its first 3D depth sensing camera as the LifeSense G53. This unit is designed to be a VGA quality, small form factor, camera. The unit is only 50 mm x 14.9 mm x 20 mm (1.97″ x 0.59″ x 0.79′) and it weighs 100 grams. With its small size and lightweight profile, the camera is designed for depth capture and object tracking for industrial, robotics and other applications driven by AI.
First camera in a new lineup
eCapture plans to introduce a full range of depth map cameras over the next quarter to address the growing need for stereo imaging equipment, and to capture market share in light of the recent uncertainty within the Intel RealSense product line. In September 2021, the eCapture G100 will come to market. The G100 will featured HD quality imaging.
“The surging industrial market opportunity provides immense opportunities for the eCapture line of 3D depth sensing cameras. Applications such as robotics, drones, facial recognition, smart retail, 3D scene learning, and autonomous guided vehicles all are growing and require the type of high-quality cameras we create,” said James Wang, Chief Strategy Officer of eYs3D.
Small size and affordable camera
The G53 provides a 50-degree field of view (FOV) and includes two mono sensor pairs for various resolutions of stereo, mono and depth disparity/distance map output via USB. The camera is designed for robot guidance and obstacle avoidance for automated guided vehicles (AGV) and AMRs. The camera uses a global Shutter sensor setup to allow responses to moving objects, while providing the accuracy necessary to guide the robot.
G53 Camera – Technical Specifications
|Depth Technology||Active IR Stereo ( Global Shutter )|
|Depth FOV (H x V)||H50 x V32.5|
|Depth Output Resolution & Frame Rate||Up to 640 x 400 ( USB End Point 2 streaming out )
Up to 30FPS ( Supports various *color image + depth map modes )
|RGB Output||640 x 400 or Left+Right 1280 x 400 ( USB End Point 1 streaming out )|
|Minimum Depth Distance (Min-z)||15cm, Varies depending on MTF Index|
|Maximum Range||200cm, Varies depending on performance accuracy & ambient conditions|
|Total Power||< 2.00W|
Several leading consumer robotics companies recently incorporated eCapture cameras with depth vision to their cleaning robot design. The solution’s global Shutter (GS) sensor setup and wide Field-of-View (FoV) allow responses to quick motion objects, which is an important function for this application, allowing the devices to react to sudden turn behavior, for example.
eCapture camera solutions are based on the innovative eYs3D stereo vision processing solutions. The eYs3D vision processor can compute the stereo depth map data and reduces the burden on the host CPU/GPU, allowing for higher performance and lower power solutions. Synchronized frame data from both cameras allows development of SLAM algorithms.
The camera has an open API and is designed to work with MediaPipe (Google) to efficiently train new vision recognition models. Applications include:
- Face detection
- Face mesh
- Hand tracking
- Object detection
- Iris tracking
The new G53 camera is available with pricing starts at $79 with a special sample promotional price for Sept. 2021 of $49 for the first 50 buyers. The company is also offering an IP67 housing option, for industrial applications, for an additional $70.
Identify possible Off the shelf stereo sensors with an open sdk. We should be able to tweak configurations to vary depth resolution.