This study focuses on enhancing the quality of video images in coal mines under challenging conditions such as dust and low illumination. Existing algorithms often suffer from poor generalization and low accuracy. To address these limitations, we propose an unsupervised image enhancement method based on the HSV color space transformation, incorporating the Retinex theory into the luminance component (V channel). A disturbance technique is employed to perturb the luminance, and a reflectance estimation network based on U-Net is designed to ensure consistency between the original reflectance and the disturbed reflectance within the same scene. Additionally, residual multiscale and attention mechanism modules are introduced to improve accuracy while reducing the network’s parameter count. The saturation component (S channel) is adaptively adjusted based on the correlation coefficient. The final enhanced image is obtained by recombining the original hue (H channel), luminance, and saturation before converting to the RGB color space. Importantly, our algorithm does not require training on normal light images. The experimental results indicate that our algorithm outperforms other state-of-the-art algorithms in terms of objective quality metrics, namely Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). Additionally, our algorithm exhibits superior performance in subjective visual analysis compared to the comparative algorithms, demonstrating its efficacy in improving the visual quality of low-light images in mining environments.

The dim lighting and excessive dust in underground mines often result in uneven illumination, blurriness, and loss of detail in surveillance images, which hinders subsequent intelligent image recognition. To address the limitations of the existing image enhancement algorithms in terms of generalization and accuracy, this paper proposes an unsupervised method for enhancing mine images in the hue–saturation–value (HSV) color space. Inspired by the HSV color space, the method first converts RGB images to the HSV space and integrates Retinex theory into the brightness (V channel). Additionally, a random perturbation technique is designed for the brightness. Within the same scene, a U-Net-based reflectance estimation network is constructed by enforcing consistency between the original reflectance and the perturbed reflectance, incorporating ResNeSt blocks and a multi-scale channel pixel attention module to improve accuracy. Finally, an enhanced image is obtained by recombining the original hue (H channel), brightness, and saturation (S channel), and converting back to the RGB space. Importantly, this image enhancement algorithm does not require any normally illuminated images during training. Extensive experiments demonstrated that the proposed method outperformed most existing unsupervised low-light image enhancement methods, qualitatively and quantitatively, achieving a competitive performance comparable to many supervised methods. Specifically, our method achieved the highest PSNR value of 22.18, indicating significant improvements compared to the other methods, and surpassing the second-best WCDM method by 10.3%. In terms of SSIM, our method also performed exceptionally well, achieving a value of 0.807, surpassing all other methods, and improving upon the second-place WCDM method by 19.5%. These results demonstrate that our proposed method significantly enhanced image quality and similarity, far exceeding the performance of the other algorithms.

In complex terrain environments such as high mountains and hills, traditional agricultural machinery cannot accurately complete tasks such as crop management and harvesting. This paper used plant protection drones as carriers to study the observation content of crops during their navigation process. Aiming at the low accuracy of the traditional quaternion cubature Kalman filtering algorithm for the attitude estimation of the carrier nonlinear state model, a quaternon-based square root cubature Kalman filtering algorithm was proposed in this paper. The algorithm takes the attitude quaternion error and the gyro drift error as the state quantity, and measures the attitude quaternion of SINS/SLAM navigation. The square root cubature Kalman filter algorithm is used for pose estimation, which not only solves the standardization problem of traditional quaternion, but also reduces the state dimension and complexity of the square root UKF algorithm of traditional quaternion, and improves the numerical stability. Compared with the quaternion SRUKF and quaternion SRCDKF algorithm, the simulation results showed that the new algorithm estimated the error mean values of the roll angle, pitch angle and runt angle, which are 0.05?, 0.08?, and 0.03?, respectively. The error is the smallest, and algorithm accuracy is about 30% higher than the quaternion SRUKF-SLAM algorithm, and it has high filtering accuracy and numerical stability, and the best time-consuming performanc.

Under the large noise, the system's observability is weak, which leads to the instability of the filtering algorithm and the slow convergence speed. The algorithm of simultaneous localization and mapping based on the square-root Cubature Kalman filter (SRCKF) with Spherical Simplex(SS) was proposed in this paper. It not only abandoned the intercept term of traditional filtering algorithm, but also avoided the large amount of computation in sigma point algorithm. The new algorithm was used in the navigation, and the simulation experiment results and data showed that the number of sampling points and the amount of calculation were reduced because of the hypersphere distribution sampling. At the same time, the square root decomposition guaranteed the non-negative of the matrix, and the algorithm had s a good stability and a certain navigation precision.

Achieving both high energy efficiency and extended battery lifespan remains a major challenge in distributed in-wheel motor electric vehicles. This study proposes a hybrid multi-objective optimization framework combining the Asynchronous Advantage Actor–Critic (A3C) algorithm with an Improved Sparrow Search Algorithm (ISSA). The A3C algorithm performs real-time torque allocation to maximize instantaneous energy efficiency, while the ISSA optimizes long-term battery management strategies by explicitly embedding capacity fading and thermal safety constraints. To coordinate these conflicting objectives across different time scales, a dynamic weight adjustment mechanism and a cross-scale shared memory pool are introduced. Simulation results under NEDC, WLTC, and CLTC driving cycles demonstrate that the framework significantly outperforms conventional algorithms in terms of convergence speed, energy consumption reduction, and battery durability. Furthermore, Hardware-in-the-Loop (HIL) experiments confirm the framework’s excellent real-time performance and control accuracy on a physical controller, validating its engineering feasibility.