The active contour model (ACM) approach in image segmentation is regarded as a research hotspot in the area of computer vision, which is widely applied in different kinds of applications in practice, such as medical image processing. The essence of ACM is to make use ofuse an enclosed and smooth curve to signify the target boundary, which is usually accomplished by minimizing the associated energy function by means ofthrough the standard descent method. This paper presents an overview of ACMs for handling image segmentation problems in various fields. It begins with an introduction briefly reviewing different ACMs with their pros and cons. Then, some basic knowledge in of the theory of ACMs is explained, and several popular ACMs in terms of three categories, including region-based ACMs, edge-based ACMs, and hybrid ACMs, are detailedly reviewed with their advantages and disadvantages. After that, twelve ACMs are chosen from the literature to conduct three sets of segmentation experiments to segment different kinds of images, and compare the segmentation efficiency and accuracy with different methods. Next, two deep learning-based algorithms are implemented to segment different types of images to compare segmentation results with several ACMs. Experimental results confirm some useful conclusions about their sharing strengths and weaknesses. Lastly, this paper points out some promising research directions that need to be further studied in the future.

The lack of grasp of the image information and the unstable fluctuation of the model energy may cause segmentation failure of the active contour model (ACM). Minimizing the impact of these two factors is critical. A local pre-piecewise fitting (LPPF) bias correction model for fast and accurate segmentation is proposed in this paper. It defines a pre-fitting function of local regions and an energy function. The grayscale information of small areas in the image is fully extracted, so that the contour accurately locates the target. Then, the optimal solution to the estimated value of the bias field is obtained. The real image information is described by the bias field, and the energy function of the model is constructed. The optimized distance regularized term and neighborhood average filtering method are utilized to achieve level set function regularization and contour smoothing. This optimization process reduces the amount of calculation and improves the robustness of LPPF model. Experiments are performed to verify that LPPF model has strong robustness to initial contours and has ability to segment blurry images while satisfactory segmentation efficiency and accuracy are obtained.

In the present article, this paper provides a method for fast image segmentation for computer vision, which is based on a level set method. One dominating challenge in image segmentation is uneven illumination and inhomogeneous intensity, which are caused by the position of a light source or convex surface. This paper proposes a variational model based on the Retinex theory. To be specific, firstly, this paper figures out the pre-fitting reflectance by using an algorithm in the whole image domain before iterations; secondly, it reconstructs the image domain using an additive model; thirdly, it uses the deviation between the global domain and low-frequency component to approximate the reflectance, which is the significant part of an energy function. In addition, a new regularization term has been put forward to extract the vanishing gradients. Furthermore, the new regularization term is capable of accelerating the segmentation process. Symmetry plays an essential role in constructing the energy function and figuring out the gradient flow of the level set.

The significant weaknesses of the active contour model are the manual setting of contour and the inability to process images with complex information, which limits its efficiency and application scope. In this paper, an ACM, called FSC&NDF, is combined with fuzzy superpixel centers (FSC) and nonlinear diffusion filter (NDF) to solve the above two problems simultaneously. YOLOv9 is adopted to locate the superpixels of interest, the joint boundaries of these superpixels are set as the initial contour, which is close to the morphological features of the target. Improved fuzzy superpixel clustering is applied to extract image features and yield superpixel centers, and the clusters are integrated into the main body of the energy function, NDF module further enhances boundary positioning and suppresses noise. In addition, the proposed connection mechanism makes it possible to convert object detection to instance segmentation. Experimental results show that FSC&NDF overcomes the limitations of previous ACMs in all aspects and its FPS, AP, AP₅₀, and AP_M are higher than mainstream deep learning algorithms. The platform experiment based on the telecentric lens further proves the practicality of FSC&NDF.

Mobile robots face collision risk avoidance challenges in dynamic environments, necessitating that we address the safety and adaptability shortcomings of traditional navigation methods. Traditional methods rely on predefined rules, making it difficult to achieve flexible, safe, and real-time obstacle avoidance in complex, dynamic environments. To address this issue, a risk-aware, dynamic, adaptive regulation barrier policy optimization (RADAR-BPO) method is proposed, combining proximal policy optimization (PPO) with the control barrier function (CBF). RADAR-BPO generates exploratory actions using PPO and constructs a real-time safety filter using the CBF. This method uses quadratic programming to minimize risky actions, thereby ensuring safe obstacle avoidance while maintaining navigation efficiency. Testing of three phased learning environments in the ROS Gazebo simulation environment demonstrated that the proposed method achieves an obstacle avoidance success rate of nearly 90% in complex, dynamic, multi-obstacle environments and improves the overall mission success rate, validating its robustness and effectiveness in complex dynamic scenarios.