ROI-based AE and HDR technologies elevate the capabilities of embedded vision applications. By combining targeted exposure adjustments with enhanced dynamic range, these features empower embedded vision systems to achieve superior imaging results. Ultimately, this drives innovation in markets such as industrial, medical, surveillance, and more.
In our previous blog, you learned about the role of ROI in optimizing camera exposure, focus, and cropping. In this blog, you’ll discover the impact of ROI-based AE on HDR performance.
You’ll also see how e-con Systems’ See3CAM_CU81 supports this capability to enhance the performance of embedded vision systems.
How ROI-Based Auto Exposure Works
ROI-based AE enhances exposure control by concentrating on defined regions within an image frame. It adjusts exposure settings dynamically by identifying areas of higher relevance within the scene, thereby optimizing for brightness and clarity in those sections.
This minimizes the effects of overexposure and underexposure in surrounding regions, which helps strike a balance that highlights crucial visual information.
The image below illustrates how selecting an ROI helps balance exposure by adapting to lighting variations.
Figure 1: ROI-based Exposure Control
How HDR Helps Expand the Dynamic Range
High Dynamic Range (HDR) complements ROI-based AE by capturing multiple images at varying exposure levels and merging them into a single frame. The resulting image retains important details across shadows and highlights, providing balanced visibility in scenes with high contrast.
e-con Systems’ See3CAM_CU81: ROI-Based AE in Action
See3CAM_CU81, a 4K HDR USB camera from e-con Systems, integrates ROI-based AE seamlessly. It supports HID controls for configuring and retrieving the AE ROI mode.
These functionalities are accessible through the e-CAMView application, a Windows DirectShow-based USB camera software for video streaming and image capture.
Figure 2: Auto Exposure ROI in e-CAMView Application
The camera’s ROI AE mode operates exclusively when auto exposure is active, ensuring an optimized capture experience.
The window size defines the size of the ROI. For window size 8, the entire frame will be the ROI. If this region exceeds or decrease, the frame boundary of the ROI will be clipped automatically.
For frame size 1280 x 720, the exposure region based on the window size is listed in below table.
| Window Size | Exposure Region (1280 x 720) |
| 1 | 1/8 (160 x 90) |
| 2 | 2/8 (320 x 180) |
| 3 | 3/8 (480 x 270) |
| 4 | 4/8 (640 x 360) |
| 5 | 5/8 (800 x 450) |
| 6 | 6/8 (960 x 540) |
| 7 | 7/8 (1120 x 630) |
| 8 | 1 (1280 x 720) |
Impact of ROI-Based AE on HDR Performance of Embedded Vision Systems
Industrial Automation
ROI-based AE ensures exposure settings prioritize key regions of interest, such as areas containing critical product features or assembly points. Along with HDR, which preserves details in high-contrast scenarios, embedded vision systems can capture fine details even under harsh lighting, like glare from machinery or uneven illumination on production lines.
For example, conveyor belt monitoring benefits from ROI-based AE by focusing exposure on product edges or labels. It ensures consistent and accurate analysis regardless of varying light conditions.
Medical Imaging
ROI-based AE enables these systems to concentrate on specific anatomical regions, ensuring clear visualization of areas requiring attention. When combined with HDR, the result is improved imaging in environments with varying light levels, such as shadowed tissue structures and illuminated surgical fields.
For instance, in endoscopy, ROI-based AE helps maintain consistent exposure in specific areas, while HDR ensures that illuminated and shadowed regions retain their details.
Surveillance and Security Systems
Surveillance systems tend to operate in environments with highly dynamic lighting conditions, such as dim indoor areas, outdoor spaces with bright sunlight, or transitional zones between them. ROI-based AE focuses on priority regions, such as entryways, license plates, or facial features, while HDR ensures clear visualization of details across bright and shadowed areas.
This can be extremely useful for security personnel who rely on real-time video feeds for monitoring. For example, an embedded vision system equipped with ROI-based AE can prioritize exposure on a moving subject while HDR ensures surrounding areas remain visible.
e-con Systems’ See3CAM_CU81: An AR0821 sensor-based 4K HDR USB Camera
e-con Systems has been designing, developing, and manufacturing OEM cameras since 2003. Our See3CAM_CU81 is a 4K HDR USB 3.1 Gen 1 camera based on the AR0821 CMOS color image sensor from onsemi®. Its built-in Image Signal Processor supports auto exposure and auto white balance for delivering optimized image quality with minimal noise, even in low light.
This plug-and-play camera ensures reliable transmission of uncompressed and compressed video data with a fixed focus and interchangeable M12 lens.
e-con Systems’ See3CAM_CU81 is ideal for applications like Kiosks, Retail Automation, Telepresence, Auto Farming, and sports analytics since it performs exceptionally well in scenarios that demand high-resolution data capture.
Explore our Camera Selector Page to see our full portfolio.
Need help integrating the best camera solution into your embedded vision system? Please write to camerasolutions@e-consystems.com.
Prabu is the Chief Technology Officer and Head of Camera Products at e-con Systems, and comes with a rich experience of more than 15 years in the embedded vision space. He brings to the table a deep knowledge in USB cameras, embedded vision cameras, vision algorithms and FPGAs. He has built 50+ camera solutions spanning various domains such as medical, industrial, agriculture, retail, biometrics, and more. He also comes with expertise in device driver development and BSP development. Currently, Prabu’s focus is to build smart camera solutions that power new age AI based applications.