Youtor
SceneScan – 3D Sensing with Stereo Vision
>> YOUR LINK HERE: ___ http://youtube.com/watch?v=mJ5UlXNguvg
With SceneScan and SceneScan Pro Nerian Vision Technolgoies introduces a new innovative sensor solution for 3D depth perception. SceneScan is an embedded processing system that connects to two standard industrial cameras or Nerian's own Karmin2 stereo camera. Similar to the human visual system, SceneScan is able to infer the depth of the observed scene by comparing the images of both cameras. This enables SceneScan to provide a depth estimate for each observed camera pixel. The resulting depth map is transferred through a gigabit ethernet link to a computer or an embedded system for onward processing. • SceneScan is based on a dedicated hardware implementation of the popular Semi-Global Matching (SGM) algorithm for computer stereo vision, which leads to an unprecedented processing performance. This allows SceneScan to compute depth estimates for up to 30 million pixels per second. At the same time, the processing results are available at a very low latency and thanks to the custom hardware solution the system has a particularly low power consumption. • Most depth sensors that are in industrial use today are based on active sensing methods. Commonly these sensors employ structured lighting or time-of-flight (ToF) measurements. In both cases, light is emitted and then its reflection is captured by an image sensor. This makes these system sensitive to the current lighting conditions. Depth measurements are only possible if there is sufficient contrast between the current ambient light and the light that is emitted by the sensor. This means that such systems cannot be used in situations with very bright lighting, such as outdoors at sunshine. • Another limitation that follows from employing active lighting is the limited range. With increasing distance the light that is emitted by the sensor is spread over an ever increasing area. As the amount of light that the sensor can supply is limited, there exists a firm limit on the maximum range that can be observed. • In contrast stereo vision, as being a passive sensing method, does not have a limit on the maximum range that can be observed. The only limit for this technology is the depth resolution, which decreases with increasing distance. Because we allow the user to choose their own camera setup, the depth resolution can be controlled and it is possible to choose configurations that provide high depth resolutions even for high distances. Other advantages of stereo vision are that multiple sensors do not interfere with one another, and that only one single exposure is required from each image sensor, which allows for the observation of quickly moving objects. • Learn more at: https://nerian.com/products/scenescan...
#############################
