Drone imagery is increasingly used in automated inspection for infrastructure surface defects, especially in hazardous or unreachable environments. In machine vision, the key to crack detection rests with robust and accurate algorithms for image processing. To this end, this paper proposes a deep learning approach using hierarchical convolutional neural networks with feature preservation (HCNNFP) and an intercontrast iterative thresholding algorithm for image binarization. First, a set of branch networks is proposed, wherein the output of previous convolutional blocks is half-sizedly concatenated to the current ones to reduce the obscuration in the down-sampling stage taking into account the overall information loss. Next, to extract the feature map generated from the enhanced HCNN, a binary contrast-based autotuned thresholding (CBAT) approach is developed at the post-processing step, where patterns of interest are clustered within the probability map of the identified features. The proposed technique is then applied to identify surface cracks on the surface of roads, bridges or pavements. An extensive comparison with existing techniques is conducted on various datasets and subject to a number of evaluation criteria including the average F-measure ( $AF_\beta $ ) introduced here for dynamic quantification of the performance. Experiments on crack images, including those captured by unmanned aerial vehicles inspecting a monorail bridge. The proposed technique outperforms the existing methods on various tested datasets especially for GAPs dataset with an increase of about 1.4% in terms of $AF_\beta $ while the mean percentage error drops by 2.2%. Such performance demonstrates the merits of the proposed HCNNFP architecture for surface defect inspection.

This paper presents a novel and feasible path planning technique for a group of unmanned aerial vehicles (DAVs) conducting surface inspection of infrastructure. The ultimate goal is to minimise the travel distance of DAVs while simultaneously avoid obstacles, and maintain altitude constraints as well as the shape of the UAV formation. A multiple-objective optimisation algorithm, called the Angle-encoded Particle Swarm Optimization (θ- PSO) algorithm, is proposed to accelerate the swarm convergence with angular velocity and position being used for the location of particles. The whole formation is modelled as a virtual rigid body and controlled to maintain a desired geometric shape among the paths created while the centroid of the group follows a pre-determined trajectory. Based on the testbed of 3DR Solo drones equipped with a proprietary Mission Planner, and the Internet-of- Things (loT) for multi-directional transmission and reception of data between the DAV s, extensive experiments have been conducted for triangular formation maintenance along a monorail bridge. The results obtained confirm the feasibility and effectiveness of the proposed approach.