A cascaded GRU-based stereoscopic matching network for precise plank measurement

Abstract

Wooden plank images in industrial measurements often contain numerous textureless areas. Furthermore, due to the thin plate structure, the three-dimensional disparity of these planks is predominantly confined to a narrow range. Consequently, achieving accurate three-dimensional matching of wooden plank images has consistently presented a challenging task within the industry. In recent years, deep learning has progressively supplanted traditional stereo matching methods due to its inherent advantages, including rapid inference and end-to-end processing. Nonetheless, the acquisition of datasets for stereo matching networks poses an additional challenge, primarily attributable to the difficulty in obtaining accurate disparity data. Thus, this paper presents a novel stereo matching method incorporating three key innovations. Firstly, an enhanced Gated Recurrent Unit(GRU) network is introduced, accompanied by a redesigned structure to achieve higher matching accuracy. Secondly, an efficient preprocessing module is proposed, aimed at improving the algorithm's efficiency. Lastly, in response to the challenges posed by datasets acquisition, we innovatively employed image simulation software to obtain a high-quality simulated dataset of wooden planks. To assess the feasibility of our approach, we conducted both simulated and real experiments. The experiments results clearly exhibit the superiority of our method when compared to existing approaches in terms of both stability and accuracy. In the simulation experiment, our method attained a bad1.0 score of 2.1% (compared to the baseline method's 9.76%); In the real experiment, our method achieved an average error of 0.104mm (compared to the baseline method's 0.268mm). It is worth noting that our study aims to address the challenge of acquiring datasets for deep learning and bridging the gap between simulated and real data, resulting in increased applicability of deep learning in more industrial measurement domains.

Estimation of lithium battery state of charge using the LTG-SABO-GRU model

“…This paper employs the root mean square error (RMSE) and mean absolute error (MAE), as delineated in equations ( 4) and ( 5), as the indicators for evaluating the SOC estimation precision of various models: the GRU model, PSO-GRU model, BO-GRU model, and LTG-SABO-GRU model. Notably, the hyperparameters for the GRU model were set in accordance with established literature [32,33], with a learning rate of 0.001, a hidden node count of 100, and a batch processing size of 16,…”