High-precision, real-time, and long-range target geo-location is crucial to UAV reconnaissance and target strikes. Traditional geo-location methods are highly dependent on the accuracies of GPS/INS and the target elevation, which restricts the target geo-location accuracy for LRORS. Moreover, due to the limitations of laser range and the common, real time methods of improving the accuracy, such as laser range finders, DEM and geographic reference data are inappropriate for long-range UAVs. To address the above problems, a set of work patterns and a novel geo-location method are proposed in this paper. The proposed method is not restricted by conditions such as the accuracy of GPS/INS, target elevation, and range finding instrumentation. Specifically, three steps are given, to perform as follows: First, calculate the rough geo-location of the target using the traditional method. Then, according to the rough geo-location, reimage the target. Due to errors in GPS/INS and target elevation, there will be a re-projection error between the actual points of the target and the calculated projection ones. Third, a weighted filtering algorithm is proposed to obtain the optimized target geo-location by processing the reprojection error. Repeat the above process until the target geo-location estimation converges on the true value. The geo-location accuracy is improved by the work pattern and the optimization algorithm. The proposed method was verified by simulation and a flight experiment. The results showed that the proposed method can improve the geo-location accuracy by 38.8 times and 22.5 times compared with traditional methods and DEM methods, respectively. The results indicate that our method is efficient and robust, and can achieve high-precision target geo-location, with an easy implementation.

With the advantages of ultrahigh resolution and acquisition rate, line scan cameras are increasingly being deployed for precision measurement. In order to achieve high precision, the intrinsic parameters must be calibrated properly. However, the existing calibration models that only calibrate the principle points and the distortion on one-dimensional direction and ignore the other directions result in limited adaptability and accuracy, which are especially serious for multiline cameras. To conquer this challenge, this paper proposes a precise calibration method which is qualified both for multiline cameras and single-line cameras. Through the analysis of the relative position relationship between pixel array and principle point, a method for calibrating the principle points and the distortion on two-dimensional direction is proposed and a flexible calibration device is designed based on a theodolite. The calibration quality is improved by the novel calibration method which effectively establishes the correspondence relationship between the rays and pixels by recording incident angle of collimated beam and its image respectively. Moreover, a robust optimization algorithm is proposed to enhance the stability of parameter estimation. The proposed method is verified by Monte-Carlo simulation, real experimental data and flight, the results show that the two-dimensional calibration model can improve the calibration accuracy of the multiline cameras by 45 pixels at most and its re-projection measurement uncertainty is as low as 0.1 pixels. The comparative results of the experiments demonstrate that the proposed method has the advantages of high accuracy, low cost, and easy implementation.

A vehicle detection algorithm was proposed based on the morphology and wavelet transform, in the context of the traditional difference. First, the background model was established, using statistical means of the rapid sequence. As background to transform the impact of light obviously, the corresponding easy and quick to update the background algorithm was used. Using the background of the video images to do background subtraction, and then images of the vehicles were accurate detection of mathematical morphology and wavelet transform. A video vehicle detection system was developed using visual C++6.0 and OpenCV image and development kits. A highway traffic flow has been detected by a background extraction, image filtering, image binary, morphological transformation, vehicle detection and segmentation methods and steps. To achieve some highway traffic flow analysis, results showed that: the system to identify the correct rate of more than 98 percent, satisfying the requirements of practical applications.

Object detection is a basic and important task in the field of aerial image processing and has gained much attention in computer vision. However, previous aerial image object-detection approaches have insufficient use of scene semantic information between different regions of large-scale aerial images. In addition, complex background and scale changes make it difficult to improve detection accuracy. To address these issues, we propose a relationship representation network for object detection in aerial images (RelationRS): (1) Firstly, multi-scale features are fused and enhanced by a dual relationship module (DRM) with conditional convolution. The dual relationship module learns the potential relationship between features of different scales and learns the relationship between different scenes from different patches in a same iteration. In addition, the dual relationship module dynamically generates parameters to guide the fusion of multi-scale features. (2) Secondly, the bridging visual representations module (BVR) is introduced into the field of aerial images to improve the object detection effect in images with complex backgrounds. Experiments with a publicly available object detection dataset for aerial images demonstrate that the proposed RelationRS achieves a state-of-the-art detection performance.