N+Half BNN: An ultra-lightweight binary neural network for traffic signal recognition

The advancement of intelligent cockpit systems has driven the integration of numerous multimedia and perceptual devices, creating stringent demands for real-time data processing. To enable prompt responses to user inputs and environmental dynamics, associated algorithms must be deployed locally on vehicular platforms rather than depending on cloud computation. The design paradigm for such models is evolving from a narrow pursuit of accuracy toward a multi-objective framework that balances inference latency, energy efficiency, and performance. Herein, we propose an ultra-lightweight binary neural network (BNN) model designed for hardware deployment, and conduct image classification research based on the German Traffic Sign Recognition Benchmark (GTSRB) dataset. In addition, we also verify it on ImageNet100 datasets. The proposed model shows excellent recognition performance with an accuracy of up to 97.64%, making it one of the best performing BNN models in the GTSRB dataset. Compared with the full-precision model, the accuracy loss is controlled within 1%, and the parameter storage overhead of the model is only 10% of that of the full-precision model. More importantly, our network model only relies on logical operations and low-bit width fixed-point addition and subtraction operations during the inference phase. The source code and trained models are publicly available at: https://github.com/1510181330/N-Half.git .