Argel A. Bandala

Vehicle parking inventory system utilizing image recognition through artificial neural networks

An automated vehicle logging system is introduced in this paper. The system utilizes character recognition through images captured from the entrance of a parking area. These images are processed to extract the licensed plates of any vehicle entering the parking area. Extracted plates images are then converted into numerical forms devised by researchers to fit the requirements of the artificial neural network. From the numbered plate, each character is then extracted to produce their distinct features. Character recognition engine is primarily implemented using feed forward neural networks. There are 50 input neurons which are defined by resizing each character into 25×25 pixel image and summing all the pixel values in each row and each columns resulting to 50 sums. After which a numerical value will be produce and will signify a character equivalent. Characters are recognized separately. This process is done until all of the characters are recognized. Afterwards, these characters are then concatenated to produce the plate number identity. The system is trained using 5860 sets of training data yielding a system with 0.0001645724% error.

Swarming Algorithm for Unmanned Aerial Vehicle (UAV) Quadrotors : Swarm Behavior for Aggregation, Foraging, Formation, and Tracking

This paper presents the fusion of swarm behavior inmulti robotic system specifically the quadrotors un-manned aerial vehicle (QUAV) operations. This studydirected on using robot swarms because of its key fea-ture of decentralized processing amongst its member.This characteristicleadstoadvantagesofrobotopera-tionsbecauseanindividual robotfailurewill notaffectthe group performance. The algorithm emulating theanimal or insect swarm behaviors is presented in thispaper and implemented into anartificial roboticagent(QUAV) in computer simulations. The simulation re-sults concluded that for increasing number of QUAVthe aggregation accuracy increases with an accuracyof 90.62%. The experiment for foraging revealed thatthe number of QUAV does not affect the accuracy ofthe swarm instead the iterations needed are greatlyimproved with an averageof 160.53iterations from 50to 500 QUAV. For swarm tracking, the average accu-racy is 89.23%. The accuracy of the swarm forma-tion is 84.65%. These results clearly defined that theswarmsystemis accurateenoughto performthe tasksand robust in any QUAV number.Keywords: swarm robotics, swarm intelligence, socialbehaviors, unmannedaerial vehicles

Machine vision for traffic violation detection system through genetic algorithm

This paper presents a machine vision algorithm to detect traffic violations specifically swerving and blocking the pedestrian lane. The proposed solution consists of background difference method, and focuses on the genetic algorithm of the system to detect these violations. The general process is as follows: a capture picture is to be subtracted first by the reference image, then the genetic algorithm is run to find the violator, and finally a display is outputted with the corresponding type of violation. The machine vision traffic violation detection system was found to have an average convergence of about 8 iterations, within an average of less than 300 generations. These results show that the algorithm is well-suited for real time implementation in traffic detection system. Provided the system inputs were captured photos from a CCTV camera, whereas the outputs were cropped pictures of the car that was detected to have such violations mentioned earlier.

Blind localization method for quadrotor-unmanned aerial vehicle (QUAV) utilizing genetic algortihm

There is an increasing research interest in unmanned autonomous vehicles (UAVs) such as quadrotors. These researches applies these quadrotors for much more complicated tasks with most requiring cameras and GPS modules for positioning. This paper presents an alternative way of position localization of a quadrotor without the use of cameras and GPS modules by means of transceivers and Genetic Algorithm (GA). This paper uses the received signals from the transceivers as inputs for the genetic algorithm in order to locate the quadrotor in a xyz axis. Parameters such as location of transceivers, amount of transceivers and population size of the GA are tested in order to determine a successful way of locating the quadrotor. Results show that the different parameters tested were successful and converges to a point usually with a fitness measure greater than 99%. An average fitness measure greater than 99.9900% served as a benchmark for the tests done. The first test achieved this benchmark at about 130 generations and the second test achieved it at 110 generations. The time it took for the program to locate the quadrotor is about 60 milliseconds. Results show that this blind localization technique is successfully locates the quadrotor and may be calibrated to ones own need.

Optimization of decentralized information dissemination in quadrotor swarm using genetic algorithm

There is a glaring problem in communication systems when it comes to a decentralized robotic swarm. Since a decentralized swarm would limit the awareness of each agent to its immediate surroundings/neighbors, the exchange of information between agents may now prove to be challenging. An epidemic-based broadcasting technique is then presented to resolve the problem of end-to-end agent communication. This paper aims to optimize the information diffusion by means of implementing genetic algorithm to optimize the time it will take for each quadrotor individual to acquire the information coming from a single source (i.e. the quadrotor who first received the information from an external stimulus). The method by which this is done is epidemic in nature. Due to this, for each time there would be a signal broadcasting, the genetic algorithm would be run to determine the next ideal location of each individual. A genetic algorithm was looped several times to achieve the desired solution. The results showed that for each run of the GA, the number of quadrotors having received the information continually increased until the output converges to a fitness level. However this only worked under certain constraints that need to be weighed out properly. This includes the readjustment of the fitness and crossover functions. Also, the parameters of the GA must be well calibrated for proper output response.

A genetic algorithm approach to swarm centroid tracking in quadrotor unmanned aerial vehicles

One of the trademark behaviors of a swarm is aggregation. Aggregation is the ability to gather swarm members around a specific point in space. The goal is to keep an object, stationary or moving, at the center of the swarm. This paper presents a novel approach to centroid tracking in robotic swarms. Genetic algorithm is used in quadrotor unmanned aerial vehicles to keep the object being tracked at the center while minimizing two parameters: the distance travelled by each quadrotor and the distance of each quadrotor from the object. Centroid tracking was found to have an average error of 0.0623568 units for swarm populations ranging from 10 to 100 with the lower swarm populations exhibiting lower errors. Convergence did not exceed the maximum of 23 milliseconds for populations less than 30. These results show that the algorithm is well-suited for implementation in swarms with lower numbers of quadrotors.

Machine vision of traffic state estimation using fuzzy logic

One of the problems encountered by motorists are congested roads. Current technology cannot easily broadcast the information about which roads are heavily congested and which are not to the motorists. As such, planning of the route to take to their destinations is compromised. This paper proposes a fuzzy logic method approach to the estimation of the traffic state of a road. Images from IP cameras installed in different roads can be used to determine the state of the traffic in an area at any point in time. The vehicles within the image are needed to be detected first via edge detection. As the vehicles are detected within the image, so are their position and size with respect to the whole image are obtained. As such, three different parameters namely vehicle density, distance between neighboring vehicles and vehicle sizes can be computed. Using these three parameters, a fuzzy logic system can be created. Three degrees of intensity for each parameter was used, creating 27 rules. The center of gravity method was used to defuzzify the traffic density parameter. Based on the results, the designed algorithm was able to identify six different road images of different traffic states accurately.

Automated traffic violation apprehension system using genetic algorithm and artificial neural network

Developing countries face the problem of crowded and congested roads because of inefficient implementation of traffic rules. Motorists ignore the rules because they are not apprehended and can get away easily. This paper proposes an intelligent traffic system that is able to automatically detect and apprehend traffic violators, specifically motorists who either swerve or block the pedestrian lane. The system is designed by integrating three processes: violation detection, plate localization and plate recognition. The violation detection and plate localization were realized using genetic algorithm while the plate recognition process was performed using an artificial neural network. The recognition of the plate number is highly dependent on the position of the detected vehicle with respect to the camera. Thus, the recognized plate number will only be supplementary information about the violator; the physical attributes of the vehicle which is captured by the violation detection process will be the main information on the violator. Based on the results of 48 images tested, the overall system was able to detect the mentioned violations and to identify the plate number of the vehicles that were detected as traffic violators, with an average accuracy of 90.67%, and program runtime of 1.34 seconds.

Path planning for quadrotor UAV using genetic algorithm

Path planning in quadrotor-typed UAV is essential in navigating from initial to destination point. This will minimize the power consumption of the vehicle which is important to avoid wasted energy in a given amount of time. This paper will use Genetic Algorithm (GA) to determine the shortest path that the quadrotor must travel given one target point to save energy and time without hitting an obstacle. The obstacle is assumed to be any point within the boundary. This algorithm is effective in searching solutions in a given sample space or population. If you know the possible solutions of the problem, you can evaluate it based on its fitness until the fittest individual arrives.

A neural network approach to a cooperative balancing problem in quadrotor-unmanned aerial vehicles (QUAVs)

There is growing interest in unmanned aerial vehicles (UAVs) such as quadrotors over the past several years. Cooperation among multiple quadrotors is one of the areas of focus. This paper proposes a neural network form of control for a cooperative task done by four quadrotors and will be tested through simulations. The task at hand is a ball and plate balancing problem during flight of multiple quadrotors carrying the plate. The objective is to maintain the keep the ball at the center of the plate even if the ball is introduced at different parts of the plate. The neural network controller will output the appropriate motor speeds of the rotors based on the detected area of introduction of the ball. Results show that the artificial neural network controller successfully directs the ball towards the center of the plate. The network outputs an average deviation of 0.00924 units from the expected PWM signal strength which corresponds to a 0.249% error from the expected value.