How does an intelligent camera recognise transparent and reflective objects? SingTown Technology's OpenMV solves competition challenges

In robot competitions, vehicles or robotic arms often need to identify the position of target objects in complex backgrounds to accomplish path planning or picking tasks.

This project requires the identification of targets, which are semi-transparent acrylic hemispherical covers, approximately 10 centimeters in diameter, with a 2-centimeter border at the base. They are placed in the center of an indoor floor area measuring 4×4 meters. There can be up to three targets, and their positions are fixed.

The background is a non-solid color floor with simple patterns, which is prone to reflections and lighting interference.

To achieve precise coordinate recognition and pose estimation, the team plans to employ SingTown's OpenMV intelligent camera as the onboard vision module for real-time detection and positioning of the acrylic cover.

The system must output the central point information of the target in the image coordinate system and transmit the data to the small vehicle's main control system to achieve automatic navigation, path adjustment, or task triggering.

The robotics competition project features a transparent target detection system built upon SingTown Technology's OpenMV intelligent camera. Its computer vision and image recognition technology, by integrating reflective feature detection, edge extraction, and morphological analysis algorithms, enables precise identification of semi-transparent acrylic covers under complex lighting conditions.

Due to the strong reflectivity and weak edge contours of acrylic material, the system first employs dynamic thresholding and background adaptive algorithms to suppress interference from ground patterns. It then uses Sobel edge detection and morphological closing operations to extract the edge contours of transparent acrylic. To address reflections, the system utilizes brightness distribution and highlight detection, effectively distinguishing real boundaries from specular reflections.

After identification is complete, the program automatically calculates the centroid coordinates (x, y) of the acrylic cover within the camera's field of view and outputs them via the serial port to the SingTown car's main control board.

When detecting multiple targets, the algorithm can filter based on target area or position, identifying the cover body within the central area of the site as the primary target.

Actual measurements indicate that this solution achieves a recognition success rate of over 93% in indoor environments with uniform lighting, with a positional error of less than 1.5 centimetres (camera height from ground: 30 centimetres).

SingTown OpenMV embedded vision system operates at high speed (frame rate above 20fps), suitable for scenarios requiring edge deployment such as robotics competitions, vehicle navigation, and robotic arm grasping.

Its advantages include no need for markers, strong adaptability to transparent objects, and stable output of coordinate signals under different ground patterns, providing precise visual input for automatic control systems.