Related Experiment Video
Updated: Jul 16, 2026
07:12
High-Throughput, In-Field Screening of Photosynthetic Efficiency in Crop Plants Using an Autonomous Robot
Published on: January 9, 2026
A Lightweight Robot-View Visual Sensing Framework for CPU-Oriented License Plate Detection and Recognition in Mobile
Ziyuan Wang1, Juan Tang1, Xinzheng Cao1
1School of Mechanical and Automotive Engineering (School of Precision Manufacturing), Liaocheng University, Liaocheng 252000, China.
Sensors (Basel, Switzerland)
|July 15, 2026
Summary
This study introduces a lightweight framework for mobile robots to detect and recognize license plates efficiently on CPUs. The proposed system enhances accuracy and speed, making it ideal for robotic inspection tasks.
Area of Science:
- Computer Vision
- Robotics
- Artificial Intelligence
Background:
- Mobile inspection robots face challenges in license plate recognition due to limited computing power and difficult imaging conditions.
- Existing methods often struggle with motion blur, low resolution, and complex backgrounds.
Purpose of the Study:
- To develop a lightweight visual sensing framework for efficient CPU-oriented license plate detection and recognition in mobile robots.
- To improve the trade-off between model size, accuracy, and inference speed for robotic perception tasks.
Main Methods:
- A YOLOv8-MGL detector was created by enhancing YOLOv8n with lightweight feature aggregation and contextual modules.
- SimAM was integrated into LPRNet to improve character recognition under adverse conditions without adding parameters.
- A YOLOv8-MGL + CRNN-CTC pipeline was evaluated for end-to-end license plate string recognition.
Main Results:
- YOLOv8-MGL achieved high mAP scores (99.5% mAP50, 71.1% mAP50:95) with reduced parameters and GFLOPs compared to YOLOv8n.
- The system demonstrated real-time performance on a CPU-only platform, with YOLOv8-MGL reaching 23.98 FPS.
- The complete pipeline achieved 91.0% exact recognition accuracy on the EDRV-LP test set and 13.25 FPS processing speed.
Conclusions:
- The proposed lightweight framework offers a robust solution for license plate perception in mobile robotic inspection.
- The system achieves a favorable balance of model compactness, detection/recognition accuracy, and efficient CPU-based inference.
- This work enables practical deployment of advanced license plate recognition capabilities on resource-constrained mobile robots.
Related Concept Videos
02:16Light Acquisition
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
01:29Relative Motion Analysis using Rotating Axes-Problem Solving
Consider a crane whose telescopic boom rotates with an angular velocity of 0.04 rad/s and angular acceleration of 0.02 rad/s2. Along with the rotation, the boom also extends linearly with a uniform speed of 5 m/s. The extension of the boom is measured at point D, which is measured with respect to the fixed point C on the other end of the boom. For the given instant, the distance between points C and D is 60 meters.
Here, in order to determine the magnitude of velocity and acceleration for point...
Here, in order to determine the magnitude of velocity and acceleration for point...