Here is your first look at the editorial content for the upcoming Winter issue of Vision Spectra.





Filter Considerations for SWIR Sensors

Most CMOS sensors have sensitivity in both the visible and NIR region. When it comes to working in the NIR spectrum, these sensors have lower quantum efficiency and can easily be overpowered by any ambient visible light which will create image noise. By implementing NIR long pass filters, visible light can be prevented from reaching the imaging sensor and creating a true NIR camera. Like standard CMOS sensors, the next generation of SWIR sensors have sensitivity in multiple spectrums -- including the latest quantum dot SWIR sensors and Sony’s new IMX990/1 SenSwir sensor with sensitivity in the visible and SWIR spectrum. In this article, the authors address how to increase contrast and spectral band isolation. Working in conjunction with SWIR LEDs, users can match SWIR bandpass filters that have similar peaks to SWIR LEDs.

Key Technologies: bandpass filters, long pass filters, CMOS sensors, SWIR LEDs

FPGAs

For embedded vision, field programmable gate arrays (FPGAs) promise it all: low power, parallel operation, and the computing horsepower needed for image analysis and AI at the edge. Traditionally, though, programming FPGAs has been difficult and required special expertise. Now newly developed tools make programming easier. So, industry experts forecast an increasing use of FPGAs in embedded vision, particularly as resolutions increase, computing burdens grow, and required response times shorten.

Key Technologies: FPGAs, embedded vision

Inspecting Imaging CMOS Sensors for Cleanliness

Automatic Optical Inspection systems are used to provide automated high resolution defect recognition during the manufacturing process within the micro-electronics industry. A key element of these systems is the CMOS sensor. Before incorporating a sensor into an AOI system, it must undergo a series of performance and cleanliness checks down to the pixel level. Sensor performance tests are defined by the imaging sensor's application and consist of a series of tests within complete darkness and uniform illumination. Measurements include blemish white pixels and while clusters (several pixels.

Key Technologies: optical inspection, in-line inspection

Sweet Potato Sorting

Like most other businesses, sweet potato exporters are not impervious to labor shortages and inflation. The author examines a new process in which sweet potatoes travel down the conveyor belt in a random array and pass under an NSIX CVK5 3D camera positioned above the input conveyor. Based on Intel RealSense technology, the camera – which offers 1280 x 720 depth resolution at up to 30 fps at maximum resolution – captures 3D images of the potatoes. NSIX Vision Keys software running on an Intel Core i7-9700 industrial PC with an NVIDIA GeForce GTX 1650 graphics processing unit guides a FANUC M-3iA/6S delta robot equipped with soft grippers to make picks. For potato placement optimization, Assatec developed a custom volume fitting algorithm within has been developed within Vision Keys software. Two additional CVK5 3D cameras are positioned above the boxing area. They capture 3D images of each box being packed. The software analyzes the images and decides where to put the next potato in the box. Once the robot places a potato into a box, the system immediately begins the process of picking another potato and finding a place for it in the box.

Key Technologies: Stereo vision, 3D vision

Creating Avatars with 3D Cameras

In sports such as gymnastics, the smallest movements can have a significant impact on performance and represent the difference between winning and losing. Advanced technologies can track fluid dynamics and body motion, providing data that can help improve performance, but challenges exist in deploying such systems. The human body is complex, and adequately capturing a realistic simulation requires complex technology with a significant amount of processing power. The Athlete – Avatar system developed by human performance optimization company Falcon Pursuit combines 3D simulation software and artificial intelligence (AI) to efficiently capture data and produce full-body, 3D avatar technology that helps athletes push the bounds of human performance. To capture an athlete's movements, sensors and cameras mounted on robot arms moving around the athlete's body during the scanning process. The digital renderings produced by the system offer precise modeling of the athlete from their form, figure and 3D motion.

Key Technologies: 3D simulation software, 3d scanning

See Pricing