Accurate segmentation of endoscopic instruments is essential in robot-assisted surgery, supporting precis enavigation, enhancing safety, and advancing surgical automation. However, this task is challenging due to factors like complex environments, instrument-tissue similarity, and lighting variations. Instruments, due to their material properties, have distinct depth distributions compared to surrounding tissues. This aspect is often overlooked in monocular video segmentation methods.To address this issue, we propose EISegNet, a multi-task framework that prioritizes instrument segmentation with an auxiliary disparity estimation task. The framework integrates an asymmetric cross-attention mechanism to enhance segmentation performance by fusing features from both tasks. Moreover, by leveraging the geometric properties of motion, EISegNet adapts the stereo disparity estimation strategy for dual-view depth estimation, broadening its applicability to various endoscopic surgeries beyond laparoscopic procedures. Furthermore, EISegNet incorporates a Gaussian-weighted loss function to emphasize edge features, which are particularly challenging for disparity estimation. This function reduces overall loss and improves segmentation accuracy. Extensive cross-dataset experiments demonstrate the superior accuracy and generalization of our method, achieving a 5.97% increase in IoU (Intersection over Union). Qualitative evaluations on clinical datasets further demonstrate the promising performance in real-world scenarios.

In recent times, geometric foundation models have demonstrated remarkable performance in depth estimation tasks, benefiting from exposure to large-scale data that enables the learning of intricate geometric structures and spatial dependencies. However, their large parameter sizes and high computational complexity pose significant challenges in meeting the efficiency requirements of downstream surgical applications. Consequently, the design of a high-performance yet lightweight monocular depth estimator has become a focal point of research. To this end, we harness the rich geometric priors encoded in geometric foundation models and introduce a novel trinity distillation scheme that transfers geometric knowledge across three complementary dimensions, namely spatial, spectral and gradient, into a compact depth estimator. To further enhance prediction quality, we develop a semantic distribution alignment strategy to effectively suppress pseudo-texture artifacts arising from the limited semantic representation capability of the lightweight estimator. Extensive experiments on the SCARED, SERV-CT, Hamlyn, and C3VD datasets demonstrate that the proposed method either surpasses or achieves comparable performance to previous state-of-the-art competitors, with a smaller model size and reduced computational overhead. Code will be available at: https://github.com/ShuweiShao/LiteNet.

Despite the great prosperity and fast development of image segmentation technology, threshold selection method is still the best choice in many practical applications. The state-of-the-art threshold selection methods perform poorly in segmenting many images with different modalities, such as the magnetic resonance images, cell images, and laser line images. Thus, it is desirable to come up with a more robust method that could segment images with different modalities with the optimum accuracy. To this end, the method should be flexible and its parameters should be adjustable for different types of images. In this paper, we propose to compute the threshold based on the slope difference distribution, which is computed from the image histogram with adjustable parameters. First, the pixels are clustered based on the peaks of the slope difference distribution into different pixel classes. Second, the threshold is selected based on the valleys of the slope difference distribution to separate the pixel classes. The robustness of this threshold selection method relies on the adjustable parameters that could be calibrated to achieve the optimum segmentation accuracy for each specific type of images. The proposed threshold selection method is tested on both the synthesized images and the real images. Experimental results show that the proposed method outperforms the state-of-the-art methods as a whole.

As the wind turbine running in harsh environments, the vibration signal is often disturbed, and its own non-stationary characteristics, is not conducive to vibration signal analysis. The local mean decomposition (LMD) idea and its adaptive decomposition characteristics are introduced, and a de-noising method of vibration signal based on LMD is proposed. The denoising effect of this method is tested by AM / FM mixed simulation signal, and compared with the experiment based on dbl de-noising method and sym6 de-noising method. In addition, the de-noising effect based on the LMD method is further tested by the vibration experiment data of Case Western Reserve University, and the results are compared with those of the other two de-noising methods. The experimental results show that the de-noising method based on LMD can achieve the same denoising effect and purpose, with the de-noising methods based on dbl and based on sym6. The noise canceling effect of this proposed method is obviously better than that of the other two, and it is even better in signal-to-noise ratio (SNR) and root mean square error (RMSE). Moreover, the distortion after the signal de-noised by the proposed method is the least, which can be very good to maintain the original vibration information, with strong robustness.

Wavelet packet provides an effective representative tool for adaptive waveform analysis of a given signal. To construct an appropriate basis, the basis-selection criterion must be carefully designed. A rate-distortion based basis selection method was proposed in recent years, which can produce an optimal basis in the rate-distortion sense. However, this approach is extremely computationally intensive. Other criterions, such as the entropy based method, do not always produce an effective basis. In this work, we propose a distortion based basis-selection criterion with moderate computational complexity. Two basis selection procedures, i.e. greedy tree growing algorithm and optimal tree pruning algorithm are both evaluated. The experimental results show that, when adopting the same quantization and entropy coding methods, the coding performance of the proposed scheme is inferior to that of the rate-distortion optimized basis by only 0.11dB on the average, while the basis search procedure is sped up by a factor of 10.1 averagely

Image coding methods based on wavelet packet decomposition show more potential than those based on usual wavelet transform since wavelet packet presents an effective tool for adaptive waveform analysis. However, most of current work adopts zerotree quantization methods inside the wavelet packet framework, and these quantization methods are proved to be inappropriate for wavelet packet subbands. In this paper, we present an image coding algorithm based on a rate-distortion optimized wavelet packet decomposition and on a block-partitioning coding scheme which quantizes each subband separately. In this way, our algorithm naturally overcomes the difficulty in defining parent-child relationships for wavelet packet subbands, which exists in the zerotree based methods. The experimental results show that the proposed algorithm significantly outperforms SPIHT and JPEG2000 schemes and also surpasses recent wavelet packet based image coding algorithms, in terms of both PSNR and visual quality.