Micro-injection is one of the most efficient approaches to deliver foreign materials into zebrafish larva heart. Well-trained micro-injection technicians are required for such operation, and still the efficiency remains low and the work is laborious. As a result, automated micro-injection that is able to improve the efficiency and injection consistency is in great demand. Barriers like auto-focusing after changing of microscope magnification, accurate tracking of injection pipette, and zebrafish larva heart detection in three dimensions make the automation challenging. The proposed coarse-fine searching strategy and the depth of field optimized step lengths result in fast and accurate auto-focusing on the zebrafish and injection pipette. The injection pipette is tracked in real-time thanks to the proposed dynamical region of interest. Besides, the combination of y-Sobel filter and alpha-beta filter improves the noise resistance during pipette tracking, which helps to reduce the tracking error. With the proposed in-plane and out-of-plane heart detection algorithms, the zebrafish heart is detected in three-dimensions efficiently and the accuracy is promising. The success rate for automated zebrafish larva heart micro-injection reached 90% with the proposed visual algorithms.

One of the basic requirements of an automated parking system is to quickly and accurately detect parking spaces. With the development of deep convolutional neural networks, parking space detection systems are becoming increasingly mature. However, the existing detection systems are often too complicated, resulting in a long detection time. In order to solve this problem, this paper proposes a two-stage parking space detection system, which aims to combine the advantages of deep learning and traditional computer vision and treat parking space detection as a two-stage process. First, we take the vehicle’s circumnavigation image as input and extract the target box of the parking space key points from the global image through the YoloV11 network. Then, using the special convolution kernel proposed in this paper, the local image is convolved to obtain the direction information of the parking space. Finally, the correct parking space is deduced based on its characteristic parameters. The method in this paper achieved a detection accuracy of 98.24% on the public data set ps2.0 (Parking-slot 2.0), and the parking space inference time on a single image was only 12.3 ms. Compared with the existing methods, the two-stage parking space detection system proposed in this paper not only demonstrates higher robustness, but also significantly reduces the time required for parking space inference.

Predators in nature grip their prey in different ways, which give innovational ideas of gripping approaches in industrial applications. Octopus performs flexible gripping with the help of vacuum grippers, suction cups, which inspired a new type of microgripper for biological sample micromanipulation. The proposed gripper consists of a glass pipette and a pump driven by a step-motor. The step-motor is controlled with adaptive robust control to adjust the gripping pressure applied on the biological sample. A dynamic model is developed for the biological sample aiming for better deformation control performance. A visual detection algorithm is developed for data processing to identify the parameters in the dynamic model and the detection result of visual algorithm is also used as feedback of adaptive robust control, which diminishes the negative influence of parameter and model uncertainties. Zebrafish larva was used as the testing sample for experiment and the corresponding parameters were identified experimentally. The experimental results correlated well with the model predicted deformation curve and visual detection algorithm provided promising accuracy, which is less than $4~\boldsymbol{\mu }\text{m}$ . Adaptive robust control provides fast and accuracy response in point-to-point deformation testing, and the average responding time is less than 30 s and the average error is no larger than 1 pixel.

In the context of the convergence of multiple energy systems, the risk of power quality degradation across different stages of energy generation and distribution has become increasingly significant. Accurate identification of power quality disturbances is crucial for improving power quality and ensuring the stable operation of power grids. However, existing disturbance identification methods struggle to balance accuracy and computational efficiency, limiting their applicability in real-time monitoring scenarios. To address this issue, this paper proposes a novel disturbance recognition framework called ST-mRMR-RF. The method first applies the S-transform to convert the time-domain signal into the time-frequency domain. It then extracts spectrum, low-frequency, mid-frequency, and high-frequency components as frequency-domain features from this domain. These are fused with time-domain features to form a multi-scale feature set. To reduce feature redundancy, the Maximum Relevance Minimum Redundancy (mRMR) algorithm is applied to select the optimal feature subset, ensuring maximum category relevance and minimal redundancy. Based on this foundation, four classifiers—Random Forest (RF), Partial Least Squares (PLS), Extreme Learning Machine (ELM), and Convolutional Neural Network (CNN)—are employed for disturbance identification. Experimental results show that the feature subset selected via mRMR reduces the model’s training time by 88.91%. When tested in a white noise environment containing 21 types of power quality disturbance signals, the ST-mRMR-RF method achieves a recognition accuracy of 99.24% at a 20dB signal-to-noise ratio. Overall, this framework demonstrates outstanding performance in noise resistance, classification accuracy, and computational efficiency.