One of the bottlenecks hindering the applications (e.g., vehicle navigation) of blockchain–UCAN is privacy. A sharded blockchain can protect vehicle data to a certain extent. However, unbalanced shard loads lead to low throughput and poor feature extraction in blockchain–UCAN. This paper proposes an optimal image binarization method (OTSU-GK) to enhance image features and reduce the amount of uploaded data, thereby improving throughput. Specifically, OTSU-GK uses a Gaussian kernel method where the parameters are optimized using grid search to improve the calculation of the threshold. Additionally, we have designed a Node Load Score (NLS)-based sharding blockchain, which considers the number of historical transactions, transaction types, transaction frequency, and other metrics to balance the sharding loads and further improve throughput. The experimental results show that OTSU-GK improves by 74.3%, 58.7%, and 83% in SSIM, RMSE/MAE/AER, and throughput. In addition, it reduces IL by 70.3% compared to other methods.
Privacy is one of the bottlenecks that hinder the applications (e.g. vehicle navigation) of blockchain-UCAN. A sharded blockchain protects the privacy of vehicle data to a certain extent. However, the unbalanced shard loads leads to low throughput, and the feature extraction in blockchain-UCAN is still poor. In this paper, an optimal image binarisation method OTSU-GK is proposed to enhance image features while reducing the amount of uploaded data to further improve the throughput. Specifically, OTSU-GK employs a Gaussian kernel method, where the parameters are optimized through grid search, to optimize the calculation of the threshold. In addition, we design a Node Load Score-based (NLS) sharding blockchain, which considers the number of historical transactions, transaction types, transaction frequency and other metrics, to balance the sharding loads and further improve the throughput. The experimental results show that OTSU-GK pproximately a 50% improvement in metrics and 83% improvement in throughput compared to other methods.