Embedded Vision is an important driver of digitization and automation, it makes machines and devices autonomously by enabling them to see. Many companies and OEMs work with components and suppliers from the Far East. Historically, this geographic location allows the integration of image processing into machines and devices, cost-effectively, and efficiently. Axel Krepil, VP of Sales for FRAMOS in Munich, Germany, reports on the resulting challenges from a developers point of view - how manufacturers and customers can develop tailor-made vision, high quality, and low cost solutions directly with local partners; and, at the same time, shorten their products' time-to-market.
Smart fridges, intelligent agricultural drones, or highly sensitive industrial robots - the working prototype and the first image present special challenges for developers embedding bare sensors into their devices. In this case, small sensor modules are ready for use and they can both simplify and accelerate the process from the initial concept, to a working prototype.
Explaining is one of Dr. Frederik Schönebeck's strengths. As Field Application Engineer (FAE) at FRAMOS, he helps customers to make optimum use of image processing and create "seeing" products. It is his job to always have an answer, to point out technical connections and to be the voice between hardware and software development. In his daily work, he helps companies from various industries in equipping their machines and devices with vision.
From small sensor modules to artificial intelligence - there are different technologies and image processing algorithms to allows drones to see. Each application has different requirements for the vision system and is dependent on the available space within the drone and the required image quality. Dr. Frederik Schönebeck of FRAMOS spoke at the VDI conference on "Civil Drones in Industrial Use" and described the criteria for applications in mapping, object recognition and navigation as well as the relevance of artificial intelligence for drones.
For accurate and instantaneous sub-nanometer interferometric measurements, even in the presence of vibration and motion, 4D Technology developed a micro-polarizer array. But now, the company is excited about the high performance and low cost of Sony's IMX250 micro-polarizer sensor. 4D Technology’s main target applications demonstrate how on-chip polarization can improve and deepen imaging results.
Drones are a popular and increasingly widespread product used by consumers as well as in a diversity of industrial, military and other applications. Historically fully under the control of human operators on the ground, they're becoming increasingly autonomous as the cameras built into them find use not only for capturing footage of the world around them but also in understanding and responding to their surroundings. Combining imaging with other sensing modalities can further bolster the robustness of this autonomy.
CMOS image sensor technology has turned into the new normal. Well, not entirely... For high-end resolutions above 50 Megapixels, users still require CCD imagers to acquire high-resolution images. But now, CMOS sensors are available with high and super-high resolution, and bring numerous benefits for developers of demanding applications in terms of quality, speed, pricing, and time-to-market.
The implementation of imaging and vision solutions can be a tough road to embark on. Expert guidance is always helpful to find the right path from technology to development, and from implementation to production. Sarah Wu of FRAMOS is such an expert who is devoting most of her time every day to helping customers devise solutions from a single image sensor all the way to entire embedded vision systems.
Clearly, from an end user experience, a noisy image is not a good image. This is an issue made more difficult because of the high sensitivity of the eye for the smallest of deviations. Also, for algorithms, noise leads to more efforts in analysis and less accuracy. For a camera manufacturer, the noise contains a plethora of information about the sensor and the electronic driving it. Thus, the noise is a developer’s best friend and if carefully analyzed will lead to the best possible camera design and implicitly to the best possible image for a given sensor and electronic components.
Image sensors are available on the market in a very broad variety in type, size and performance for nearly all levels of applications and needs. From consumer sensors to industrial detectors and imagers dedicated to specific tasks, there is a huge number of devices available off-the-shelf. But there are six good reasons to have a deeper look, if a customized sensor helps to solve your imaging challenge and to achieve your vision objectives the best possible way.
The ready-to-integrate processing block for Sony’s 3rd generation CMOS Global Shutter image sensors equipped with the SLVS-EC interface accelerates the time-to-market and improves performance for vision development on XILINX FPGAs.
Selection of a sensor based on its performance is key for imaging engineers. If the chosen sensor looks right for a specific application, the next step is to evaluate that sensor to make sure it is indeed the correct choice. FRAMOS has several options available to evaluate sensors for individual applications.
1 From 2