Histogram equalization is a technique to enhance the contrast of the image by redistributing the histogram. In this paper, a fast piecewise linear histogram equalization method is introduced based on an adjustable degree of enhancement and piecewise continuous transformation functions using frequencies of different grey-levels. This method aims to address and maximize the contrast enhancement of the image by stretching the entire spectrum. For this purpose, particular nodes (bins) on the histogram are simultaneously detected that in comparison with recursive methods, it requires less computational time. Then, the particular nodes are stretched using transformation functions to align with the reference nodes. The experimental results indicate that the performance of the proposed method is promising in terms of contrast enhancement. Moreover, this method preserves the texture of various regions in the image very well through the equalization process by using the degree of enhancement. © 2020 Owner/Author.

Change detection in aerial images is the core of many remote sensing applications to analyze the dynamics of a wide area on the ground. In this paper, a remote sensing method is proposed based on viewpoint transformation and a modified Kendall rank correlation measure to detect changes in oblique aerial images. First, the different viewpoints of the aerial images are compromised and then, a local pattern descriptor based on Kendall rank correlation coefficient is introduced. A new distance measure referred to as Kendall's Tau-d (Tau distance) coefficient is presented to determine the changed regions. The developed system is applied on oblique aerial images with very low aspect angles that obtained using an unmanned aerial vehicle in two different days with drastic change in illumination and weather conditions. The experimental results indicate the robustness of the proposed method to variant illumination, shadows and multiple viewpoints for change detection in aerial images.

Interest in aerial image analysis has increased owing to recent developments in and availabilityofaerialimagingtechnologies,likeunmannedaerialvehicles(UAVs),aswellasagrowing need for autonomous surveillance systems. Variant illumination, intensity noise, and different viewpointsareamongthemainchallengestoovercomeinordertodeterminechangesinaerialimages. In this paper, we present a robust method for change detection in aerial images. To accomplish this, the method extracts three-dimensional (3D) features for segmentation of objects above a defined reference surface at each instant. The acquired 3D feature maps, with two measurements, are then used to determine changes in a scene over time. In addition, the important parameters that affect measurement, such as the camera’s sampling rate, image resolution, the height of the drone, and the pixel’sheightinformation,areinvestigatedthroughamathematicalmodel. Toexhibititsapplicability, the proposed method has been evaluated on aerial images of various real-world locations and the results are promising. The performance indicates the robustness of the method in addressing the problems of conventional change detection methods, such as intensity differences and shadows.

Speed measurement is one of the key components of intelligent transportation systems. It provides suitable information for traffic management and law enforcement. This paper presents a versatile and analytical model for a video-based speed measurement in form of the probability density function (PDF). In the proposed model, the main factors contributing to the uncertainties of the measurement are considered. Furthermore, a guideline is introduced in order to design a video-based speed measurement system based on the traffic and other requirements. As a proof of concept, the model has been simulated and tested for various speeds. An evaluation validates the strength of the model for accurate speed measurement under realistic circumstances.

 Traffic analyses, particularly speed measurements, are highly valuable in terms of road safety and traffic management. In this paper, an analytical model is presented to measure the speed of a moving vehicle using an off-the-shelf video camera. The method utilizes the temporal sampling rate of the camera and several intrusion lines in order to estimate the probability density function (PDF) of a vehicle’s speed. The proposed model provides not only an accurate estimate of the speed, but also the possibility of being able to study the performance boundaries with respect to the camera framerate as well as the placement and number of intrusion lines in advance. This analytical modelis verified by comparing its PDF outputs with the results obtained via a simulation of the corresponding movements. In addition,as aproof-of-concept, the proposed model is implemented for avideo-based vehicle speed measurement system. The experimental results demonstrate the model’s capability in terms of taking accurate measurements of the speed via a consideration of the temporal sampling rate and lowering the deviation by utilizing more intrusion lines. The analytical model is highly versatile and can be used as the core of various video-based speed measurement systems in transportation and surveillance applications.

Advanced analysis of road traffic data is an essential component of today's intelligent transportation systems. This paper presents a video-based vehicle speed measurement system based on a proposed mathematical model using a movement pattern vector as an input variable. The system uses the intrusion line technique to measure the movement pattern vector with low computational complexity. Further, the mathematical model introduced to generate the pdf (probability density function) of a vehicle's speed that improves the speed estimate. As a result, the presented model provides a reliable framework with which to optically measure the speeds of passing vehicles with high accuracy. As a proof of concept, the proposed method was tested on a busy highway under realistic circumstances. The results were validated by a GPS (Global Positioning System)-equipped car and the traffic regulations at the measurement site. The experimental results are promising, with an average error of 1.77 % in challenging scenarios.

Vehicle classification has a significant use in traffic surveillance and management. There are many methods proposed to accomplish this task using variety of sensorS. In this paper, a method based on fuzzy c-means (FCM) clustering is introduced that uses dimensions and speed features of each vehicle. This method exploits the distinction in dimensions features and traffic regulations for each class of vehicles by using multiple FCM clusterings and initializing the partition matrices of the respective classifierS. The experimental results demonstrate that the proposed approach is successful in clustering vehicles from different classes with similar appearanceS. In addition, it is fast and efficient for big data analysiS.

Object detection in aerial images, particularly of vehicles, is highly important in remote sensing applications including traffic management, urban planning, parking space utilization, surveillance, and search and rescue. In this paper, we investigate the ability of three-dimensional (3D) feature maps to improve the performance of deep neural network (DNN) for vehicle detection. First, we propose a DNN based on YOLOv3 with various base networks, including DarkNet-53, SqueezeNet, MobileNet-v2, and DenseNet-201. We assessed the base networks and their performance in combination with YOLOv3 on efficiency, processing time, and the memory that each architecture required. In the second part, 3D depth maps were generated using pairs of aerial images and their parallax displacement. Next, a fully connected neural network (fcNN) was trained on 3D feature maps of trucks, semi-trailers and trailers. A cascade of these networks was then proposed to detect vehicles in aerial images. Upon the DNN detecting a region, coordinates and confidence levels were used to extract the corresponding 3D features. The fcNN used 3D features as the input to improve the DNN performance. The data set used in this work was acquired from numerous flights of an unmanned aerial vehicle (UAV) across two industrial harbors over two years. The experimental results show that 3D features improved the precision of DNNs from 88.23 % to 96.43 % and from 97.10 % to 100 % when using DNN confidence thresholds of 0.01 and 0.05, respectively. Accordingly, the proposed system was able to successfully remove 72.22 % to 100 % of false positives from the DNN outputs. These results indicate the importance of 3D features utilization to improve object detection in aerial images for future research. CCBY