Abstract Although existing image-text retrieval methods show strong retrieval performance, they generally fail to explicitly model the subtle semantic difference within categories. To address this problem, we propose a new image-text retrieval method, called CLIP-based Semantic Refinement Method For Image-Text Retrieval (CLIP2SRITR). The proposed method consists of a modal alignment part and a semantic matching part, where the former is to learn better alignment between two modalities and the latter is to enhance the aggregation of image-text features intra-class. The pipeline helps model the distinction between image-text pairs with semantic information differences. In addition, CLIP2SRITR leverages additive angular margin for image-text retrieval loss function to maximize classification boundaries, achieving the goal of increasing intra-class similarity and inter-class variability. Through extensive experiments on three image-text benchmarks, e.g. Wikipedia, Pascal-Sentence, and NUS-WIDE, we show that CLIP2SRITR outperforms state-of-the-art methods, verifying the effectiveness of our method.

Bridge cracks can threaten transportation safety and infrastructure, leading to severe failures if not detected. Timely, accurate detection is vital for bridge safety and preventing costly repairs. Traditional methods rely on manual inspections and basic image processing, making them slow, error-prone, and unable to detect fine cracks or handle noise. Current semantic segmentation methods face challenges in accurately identifying cracks, particularly in maintaining segmentation continuity and handling localized crack features. This paper proposes an improved bridge crack segmentation algorithm based on Mask2Former, focusing on intelligent automation in bridge maintenance by preserving segmentation continuity and handling diverse crack morphologies. The Mask2Former architecture is enhanced through the introduction of a multi-scale feature fusion module, which utilizes a fusion block to process concatenated feature maps via RepBlock, strengthening feature representation, particularly for small cracks. Furthermore, a high-resolution feature processing module is integrated, employing wavelet transform convolution (WTConv) with multi-level wavelet transformations for extensive receptive field coverage. WTConv is refined with detail enhancement convolution (DEConv), which maintains parameter efficiency, along with a channel and spatial attention mechanism to better capture fine details, thus improving the segmentation of localized cracks and effectively handling background noise. Experiments on benchmark datasets demonstrate that the proposed algorithm achieves mIoU of 86.33%, F1-Score of 85.07%, and pixel accuracy of 98.70%, surpassing existing methods in fine crack detection. Ablation experiments show that both MSFM and HRFPM significantly outperform the baseline, achieving mIoU scores of 86.22% and 85.99%, and F1-scores of 84.95% and 84.65%, respectively. These results highlight the effectiveness of the proposed method in improving the robustness, accuracy, and efficiency of bridge crack segmentation, with significant potential for enhancing bridge health monitoring in transportation infrastructure.

Suffering from environmental distress like carbon emissions, traffic restrictions have been enforced extensively in distribution logistics. Reasonable arrangement of urban freight transportation can effectively improve distribution efficiency, reduce distribution costs, and alleviate the impact of traffic restrictions in distribution logistics. In response to increasingly stringent traffic restrictions, we establish a multi-objective optimization model, including the minimum distributions and the minimum carbon emissions. Given that the limits of battery capacity and cargo capacity, we build a green vehicle routing problem with soft time windows (GVRPTW) model with heterogenous fleets. In this study, three different factors, that is restricted area, travel time of vehicles, and carbon tax prices, are discussed in details. In order to solve the NP-hard model, we propose an improved ant colony optimization algorithm (IACO) by optimizing the state transition probability, and verifies the worth of the algorithm. The experimental results can explore the impacts of traffic restriction policies on the formulation of distribution scheme and offer reference opinions for the government to formulate reasonable restriction policies and better guide logistics enterprises to reduce carbon emissions.

A neural network approach to real-time collision-free navigation of holonomic 3-degree-of-freedom (DOF) robots in a nonstationary environment is proposed. This approach is based on a biologically inspired model for dynamic trajectory generation of a point robot or a multi-joint robot manipulator. The state space of the neural network is three-dimensional (3D), where two represent the spatial position in the 2D Cartesian workspace and one represents the orientation of the robot. This model is capable of generating a real-time optimal navigation path for 3-DOF robots through the dynamic neural activity landscape without explicitly optimizing any cost functions, without any learning process, and without any local collision checking procedures. Therefore it is computationally efficient. In addition, this model can deal with real-time navigation with sudden environmental changes, navigation of a robot with multiple targets, and navigation of multiple robots. The stability of the neural network is guaranteed by Lyapunov stability analysis. The effectiveness and efficiency are demonstrated through simulation studies.

A neural network approach is proposed for real-time collision-free motion planning of holonomic and nonholonomic car-like robots in a nonstationary environment. This model is capable of planning real-time robot motion with sudden environmental changes, motion of a car with multiple targets, and motion of multiple robots. The proposed neural network model is biologically inspired, where the dynamics of each neuron in the topologically organized neural network is characterized by a shunting equation or an additive equation. There are only local connections among neurons. The real-time optimal robot motion is planned through the dynamic neural activity landscape of the neural network without explicitly searching over the free workspace nor the collision paths, without explicitly optimizing any cost functions, without any prior knowledge of the dynamic environment, without any learning process, and without any local collision checking procedures. Therefore it is computationally efficient. The stability of the neural network is guaranteed by Lyapunov stability analysis. The effectiveness and efficiency of the proposed approach are demonstrated through simulation studies.

A neural network approach is proposed for real-time collision free trajectory generation in an environment with varying obstacles and moving target. This biologically inspired neural network is topologically organised. The dynamics of each neuron is characterised by a shunting equation or an additive equation. Each neuron has only local connections, and the optimal trajectories are generated without any explicitly optimising cost functions and without learning. Therefore the model is computationally efficient. The stability of the network is analytically proved using a Lyapunov function candidate. As examples, the proposed neural network is applied to trajectory formation for a mobile robot in solving maze-type problems, dynamically tracking moving target, and avoiding varying obstacles. The efficiency of the proposed approach is demonstrated through simulation and comparison studies.

To dynamically generating trajectory with collision free is very important but difficult for the robots in a nonstationary environment. In this paper, the real-time trajectory generation and obstacle avoidance are studied using biologically motivated neural network approaches. The optimal trajectory is generated through the neural dynamics of a topologically organised neural network. Each neuron of the neural net is characterised by a shunting equation or an additive equation. This model is computationally efficient and its stability is guaranteed. These neural network approaches were applied for solving maze-type problems, dynamically tracking moving target, and avoiding varying obstacles. The model parameter sensitivity and model variations are discussed. Simulations are included to demonstrate the proposed approaches.

In this paper, a neural network approach is proposed for real-time path planning of robots with safety consideration. The neural network is topologically organised, which is based on a previous biologically inspired model for dynamical trajectory generation of a mobile robot in a nonstationary environment. The state space of the neural network can be the joint space of multilink robot manipulators or the Cartesian workspace. This model is capable of dealing with multiple target problems as well. The target globally attracts the robot, while the obstacles push the robot away locally to avoid collisions. By taking into account of the clearance from obstacles, the planned "comfortable" path does not suffer either the "too close" or the "too far" problems. Each neuron has only local lateral connections. The optimal path is generated in real-time through the dynamics of the neural activity landscape without explicitly optimising any cost function. Therefore, it is computationally efficient. The stability of the network is guaranteed by the existence of a Lyapunov function. The effectiveness and efficiency are demonstrated through simulation studies.