Apr 03 2018 cs.CV
The purpose of this study is to successfully train our vehicle detector using R-CNN, Faster R-CNN deep learning methods on a sample vehicle data sets and to optimize the success rate of the trained detector by providing efficient results for vehicle detection by testing the trained vehicle detector on the test data. The working method consists of six main stages. These are respectively; loading the data set, the design of the convolutional neural network, configuration of training options, training of the Faster R-CNN object detector and evaluation of trained detector. In addition, in the scope of the study, Faster R-CNN, R-CNN deep learning methods were mentioned and experimental analysis comparisons were made with the results obtained from vehicle detection.
Apr 02 2018 cs.CY
Radio frequency identification (RFID), The real-time location of objects and ability to track motion provide a wide range of useful applications in areas such as safety, security and supply chain. In recent years, radio frequency identification technology has moved from obscurity into mainstream applications that help speed the handling of manufactured goods and materials. RFID enables identification from a distance, and unlike earlier bar-code technology, it does so without requiring a line of sight. In this paper, the author introduces the principles of RFID, discusses its primary technologies and applications.
Mar 20 2018 cs.CV
This paper describes the stages faced during the development of an Android program which obtains and decodes live images from DJI Phantom 3 Professional Drone and implements certain features of the TensorFlow Android Camera Demo application. Test runs were made and outputs of the application were noted. A lake was classified as seashore, breakwater and pier with the proximities of 24.44%, 21.16% and 12.96% respectfully. The joystick of the UAV controller and laptop keyboard was classified with the proximities of 19.10% and 13.96% respectfully. The laptop monitor was classified as screen, monitor and television with the proximities of 18.77%, 14.76% and 14.00% respectfully. The computer used during the development of this study was classified as notebook and laptop with the proximities of 20.04% and 11.68% respectfully. A tractor parked at a parking lot was classified with the proximity of 12.88%. A group of cars in the same parking lot were classified as sports car, racer and convertible with the proximities of 31.75%, 18.64% and 13.45% respectfully at an inference time of 851ms.
Feb 27 2018 cs.CY
Light sleep is a sleeping period which occurs within each hour during the sleep. This is the period when people are closest to awakening. With this being the case people tend to move more frequently and aggressively during these periods. The characteristics of sleeping stages, detection of light sleep periods and analysis of light sleep periods were clarified. The sleeping patterns of different subjects were analyzed. In this paper the most suitable moment for waking a person up will be described. The detection of this moment and the development process of a system dedicated to this purpose will be explained, and also some experimental results that are acquired via different tests will be shared and analyzed.
Apr 21 2017 cs.CV
Matching of binary image features is an important step in many different computer vision applications. Conventionally, an arbitrary threshold is used to identify a correct match from incorrect matches using Hamming distance which may improve or degrade the matching results for different input images. This is mainly due to the image content which is affected by the scene, lighting and imaging conditions. This paper presents a fuzzy logic based approach for brute force matching of image features to overcome this situation. The method was tested using a well-known image database with known ground truth. The approach is shown to produce a higher number of correct matches when compared against constant distance thresholds. The nature of fuzzy logic which allows the vagueness of information and tolerance to errors has been successfully exploited in an image processing context. The uncertainty arising from the imaging conditions has been overcome with the use of compact fuzzy matching membership functions.
Apr 21 2017 cs.NE
Genetic Algorithms are widely used in many different optimization problems including layout design. The layout of the shelves play an important role in the total sales metrics for superstores since this affects the customers' shopping behaviour. This paper employed a genetic algorithm based approach to design shelf layout of superstores. The layout design problem was tackled by using a novel chromosome representation which takes many different parameters to prevent dead-ends and improve shelf visibility into consideration. Results show that the approach can produce reasonably good layout designs in very short amounts of time.
Apr 20 2016 cs.LG
The paper presents a comparative study of the performance of Back Propagation and Instance Based Learning Algorithm for classification tasks. The study is carried out by a series of experiments will all possible combinations of parameter values for the algorithms under evaluation. The algorithm's classification accuracy is compared over a range of datasets and measurements like Cross Validation, Kappa Statistics, Root Mean Squared Value and True Positive vs False Positive rate have been used to evaluate their performance. Along with performance comparison, techniques of handling missing values have also been compared that include Mean or Mode replacement and Multiple Imputation. The results showed that parameter adjustment plays vital role in improving an algorithm's accuracy and therefore, Back Propagation has shown better results as compared to Instance Based Learning. Furthermore, the problem of missing values was better handled by Multiple imputation method, however, not suitable for less amount of data.
Dec 11 2015 cs.CV
Coverage of image features play an important role in many vision algorithms since their distribution affect the estimated homography. This paper presents a Genetic Algorithm (GA) in order to select the optimal set of features yielding maximum coverage of the image which is measured by a robust method based on spatial statistics. It is shown with statistical tests on two datasets that the metric yields better coverage and this is also confirmed by an accuracy test on the computed homography for the original set and the newly selected set of features. Results have demonstrated that the new set has similar performance in terms of the accuracy of the computed homography with the original one with an extra benefit of using fewer number of features ultimately reducing the time required for descriptor calculation and matching.
Dec 11 2015 cs.CV
Crime Scene Investigation (CSI) is a carefully planned systematic process with the purpose of acquiring physical evidences to shed light upon the physical reality of the crime and eventually detect the identity of the criminal. Capturing images and videos of the crime scene is an important part of this process in order to conduct a deeper analysis on the digital evidence for possible hints. This work brings this idea further to use the acquired footage for generating a 3D model of the crime scene. Results show that realistic reconstructions can be obtained using sophisticated computer vision techniques. The paper also discusses a number of important design considerations describing key features that should be present in a powerful interactive CSI analysis tool.
Dec 10 2015 cs.OH
Finding the position of the user is an important processing step for augmented reality (AR) applications. This paper investigates the use of different motion models in order to choose the most suitable one, and eventually reduce the Kalman filter errors in sensor fusion for such applications where the accuracy of user tracking is crucial. A Deterministic Finite Automaton (DFA) was employed using the innovation parameters of the filter. Results show that the approach presented here reduces the filter error compared to a static model and prevents filter divergence. The approach was tested on a simple AR game in order to justify the accuracy and performance of the algorithm.
A tracking system that will be used for Augmented Reality (AR) applications has two main requirements: accuracy and frame rate. The first requirement is related to the performance of the pose estimation algorithm and how accurately the tracking system can find the position and orientation of the user in the environment. Accuracy problems of current tracking devices, considering that they are low-cost devices, cause static errors during this motion estimation process. The second requirement is related to dynamic errors (the end-to-end system delay; occurring because of the delay in estimating the motion of the user and displaying images based on this estimate. This paper investigates combining the vision-based estimates with measurements from other sensors, GPS and IMU, in order to improve the tracking accuracy in outdoor environments. The idea of using Fuzzy Adaptive Multiple Models (FAMM) was investigated using a novel fuzzy rule-based approach to decide on the model that results in improved accuracy and faster convergence for the fusion filter. Results show that the developed tracking system is more accurate than a conventional GPS-IMU fusion approach due to additional estimates from a camera and fuzzy motion models. The paper also presents an application in cultural heritage context.
Dec 09 2015 cs.CY
The focus of this paper is on wearable technologies which are increasingly being employed in the medical field. From smart watches to smart glasses, from electronic textile to data gloves; several gadgets are playing important roles in diagnosis and treatment of various medical conditions. The threats posed by these technologies are another matter of concern that must be seriously taken into account. Numerous threats ranging from data privacy to big data problems are facing us as adverse effects of these technologies. The paper analyses the application areas and challenges of wearable technologies from a technical and ethical point of view and presents solutions to possible threats.
Dec 09 2015 cs.CV
Brute force matching of binary image feature descriptors is conventionally performed using the Hamming distance. This paper assesses the use of alternative metrics in order to see whether they can produce feature correspondences that yield more accurate homography matrices. Two statistical tests, namely ANOVA (Analysis of Variance) and McNemar's test were employed for evaluation. Results show that Jackard-Needham and Dice metrics can display better performance for some descriptors. Yet, these performance differences were not found to be statistically significant.