Mobile Object Detection Research Articles

Reimagining Accessibility: Leveraging Deep Learning in Smartphone Applications to Assist Visually Impaired People Indoor Object Distance Estimation

Every other aspect of life is organized around the sight. A person with vision impairment suffers severely from independent mobility and quality of life. The proposed framework combines mobile deep learning with distance estimation algorithms to detect and classify indoor objects with estimated distance in real-time during indoor navigation. The user, wearing the device with a lanyard or holding it in a way that positions the camera forward, identifies in real-time surroundings indoor objects with estimated distance and voice commentary. Moreover, the mobile framework provides an estimated distance to the obstacles and suggests a safe navigational path through voice-guided feedback. By harnessing the power of deep learning in a mobile setting, this framework aims to improve the independence of visually impaired individuals by facilitating them a higher degree of independence in indoor navigation. This study's proposed mobile object detection and distance estimation framework achieved 99.75% accuracy. This research contributes by leveraging mobile deep learning with identifying objects in real-time, classification and distance estimation, a state-of-the-art approach to use the latest technologies to enhance indoor mobility challenges faced by visually impaired people.

Energy-Efficient Object Detection and Tracking Framework for Wireless Sensor Network

Object detection and tracking is one of the key applications of wireless sensor networks (WSNs). The key issues associated with this application include network lifetime, object detection and localization accuracy. To ensure the high quality of the service, there should be a trade-off between energy efficiency and detection accuracy, which is challenging in a resource-constrained WSN. Most researchers have enhanced the application lifetime while achieving target detection accuracy at the cost of high node density. They neither considered the system cost nor the object localization accuracy. Some researchers focused on object detection accuracy while achieving energy efficiency by limiting the detection to a predefined target trajectory. In particular, some researchers only focused on node clustering and node scheduling for energy efficiency. In this study, we proposed a mobile object detection and tracking framework named the Energy Efficient Object Detection and Tracking Framework (EEODTF) for heterogeneous WSNs, which minimizes energy consumption during tracking while not affecting the object detection and localization accuracy. It focuses on achieving energy efficiency via node optimization, mobile node trajectory optimization, node clustering, data reporting optimization and detection optimization. We compared the performance of the EEODTF with the Energy Efficient Tracking and Localization of Object (EETLO) model and the Particle-Swarm-Optimization-based Energy Efficient Target Tracking Model (PSOEETTM). It was found that the EEODTF is more energy efficient than the EETLO and PSOEETTM models.

Research and Implementation of Sports Entity Simulation Based on Heterogeneous Binocular Vision

To study the value of heterogeneous binocular vision in the detection of sports targets, a Zynq-based joint software and hardware design method is proposed, and a mobile object detection system for binocular vision is developed based on it. This paper introduces the relevant technologies and theories used in the system design. First, the basic principles and various modules of the binocular stereo vision process are introduced, including camera tuning, stereo correction, stereo tuning, and telescope stereo vision. Based on the depth information, a method to detect and measure motor targets was developed. Finally, combined with the improved mobile target detection algorithm, the real-time methodology research and algorithm design to determine the target range are completed. The performance of the moving target detection system based on binocular stereo vision and the moving target detection and ranging algorithm are tested and analyzed. We know that the front and rear width of the moving target (the person tested in this paper) is at least 10 cm, while the error value of the ranging algorithm in this paper is within 6 meters, and the average error is less than 10 cm. According to the characteristics of binocular stereo vision, the farther the viewing angle is, the smaller the parallax value of the left and right image pixels will be. Therefore, the insignificant change of depth information will bring some errors to the ranging algorithm. The greater the measurement error is, the lower the percentage deviation of the measurement result is within 2%. It also shows that the target ranging algorithm in this paper can ensure good accuracy within a certain distance. Through this method, we can obtain the accurate data of moving objects in sports competition, so as to improve the training method of athletes and improve the competition results.

Environmental Factor-Based Segmentation of Images in Natural Environments

The robust segmentation of color images in a natural environment without specific constraints such as lighting or background is very important in the field of image processing and computer vision. In this paper, an environmentally adaptive image segmentation method using color invariant is proposed. The proposed method introduces a number of color invariant, such as W, C, U, N, and H, and automatically detects factors in the surrounding environment in which images such as lighting, shading, and highlights are taken. The image is then effectively split based on the edge by selecting the color invariant optimal for the detected environmental factors. In the experiment, we implemented the proposed edge-based image segmentation algorithm. Various image data taken in general environments without specific constraints were utilized as input images of the suggested system. In this study, various kinds of color images taken in different environments were tested, and each color invariant was extracted from the experiments that best expressed the environmental changes around them. As a result, a largest number of images were determined to have a change in the intensity of lighting, followed by highlights and shadows. In addition, there were a few images that determined that no special state environmental changes existed. As the results of the experiment show visually, the existing method did not correctly remove shadows and did not detect some areas of the circular shape. In addition, the existing method can also be found to be partially inaccurate in edge detection in many areas. On the other hand, the proposed method confirmed stable segmentation of images. The proposed color invariant-based image segmentation algorithm is expected to be useful in various pattern recognition areas such as face tracking, mobile object detection, gesture recognition, motion understanding, etc.

Evaluating Edge-Cloud Computing Trade-Offs for Mobile Object Detection and Classification with Deep Learning

Internet-of-Things (IoT) applications based on Artificial Intelligence, such as mobile object detection and recognition from images and videos, may greatly benefit from inferences made by state-of-the-art Deep Neural Network(DNN) models. However, adopting such models in IoT applications poses an important challenge since DNNs usually require lots of computational resources (i.e. memory, disk, CPU/GPU, and power), which may prevent them to run on resource-limited edge devices. On the other hand, moving the heavy computation to the Cloud may significantly increase running costs and latency of IoT applications. Among the possible strategies to tackle this challenge are: (i) DNN model partitioning between edge and cloud; and (ii) running simpler models in the edge and more complex ones in the cloud, with information exchange between models, when needed. Variations of strategy (i) also include: running the entire DNN on the edge device (sometimes not feasible) and running the entire DNN on the cloud. All these strategies involve trade-offs in terms of latency, communication, and financial costs. In this article we investigate such trade-offs in real-world scenarios. We conduct several experiments using deep learning models for image-based object detection and classification. Our setup includes a Raspberry PI 3 B+ and a cloud server equipped with a GPU. Different network bandwidths are also evaluated. Our results provide useful insights about the aforementioned trade-offs. The partitioning experiment showed that, overall, running the inferences entirely on the edge or entirely on the cloud server are the best options. The collaborative approach yielded a significant increase in accuracy without penalizing running costs too much.

Object tracking algorithm for a passive positioning system

We propose an algorithm for small-sized mobile object detection and trajectory parameter estimation for a passive positioning system that consists of several optical, thermal, and radio sensors. The algorithm is based on a combination of spatial and temporal processing of observation data. For spatial processing, a set of equations is solved that defines the sufficient condition for coupling the direction vectors to probable objects in the image stereo pair. Object coordinates and velocities for a single observation period are estimated. For temporal processing, the direction vectors are distributed based on connection to probable objects in a sequence of the capture intervals. The results of numerical modeling of the proposed algorithm show the advantage of combining the two approaches in comparison with the traditional object detection and tracking algorithms.

A Framework for IoT-Enabled Virtual Emotion Detection in Advanced Smart Cities

A barrier coverage has been studied widely because it provides guaranteed detection of mobile objects after a barrier is constructed. Also, many researchers have investigated the recognition of human emotion by facial expression and human gesture or motion with possible high accuracy. In particular, thanks to recent remarkable advancements of technology, it is possible to recognize human emotion by wireless signal. In this article, we introduce a new emotion-detectable framework in advanced smart cities with a concept of barrier coverage in IoT-enabled environments. The proposed framework allows IoT devices to create a virtual emotion barrier, called a VEmoBar, which is able to sense human emotion through a wireless signal and its reflection. Also, we define a problem whose goal is to form a specific number of VEmoBars which returns a maximum cumulative accuracy. To solve the problem, we propose a novel approach as well as a system initialization and then evaluate them through extensive simulations with various scenarios. Moreover, we discuss future issues and challenges toward future promising smart cities based on this virtual emotion framework.

Mobile Object Detection Using 2D and 3D Basic Geometric Figures in Colour and Grayscale

In this paper, we use TensorFlow Mobile Lite for Object Detection with datasets of basic geometric figures on iOS mobile devices. Additionally, we trained 4 datasets in 2D and 3D and we compare the accuracy of detection between using colour and grayscale image data. Also, we evaluate the detection rate using 2D and 3D for some kind of normal objects in precision and label output. We used Convolutional Neural Networks (CNN) for build the datasets and OPENCV for convert into grayscale. We value the result relation between flat and volume datasets in way of label and numeric detection, also the affectation of TensorFlow Mobile with this kind of datasets. We make comparisons based on the results of the different experiments object the detection and, in this work, TensorFlow Mobile Lite implementation does not have pseudo boxes and the reason is explained for detection purposes and accuracy adjusted to this kind of experiments.

Tracking a Moving Objects Using Foreground Detector and Improved Morphological Filter

Mobile object detection is one of the most important steps in computer vision applications such as: medical analysis human-machine interface, robotics, traffic monitoring, and more. In this article, we apply the Gaussian mixing model which is established on the background subtraction. A smoothing method was used for the pre-processing step and a morphological filter was applied to remove unwanted pixels from the background in the other to solve the problem of background noise disturbance. We also demonstrated that filtering foreground segmentation twice with the same morphological structured element but with a different width was used to improve the accuracy of the result. The results show that the proposed method is effective in detecting and tracking moving vehicles, compared to filter segmentation in the foreground only once. Several methods and algorithms have been used to solve this problem. All the methods used before have been effective but also have limits. Some of these methods lose the object when the number of frames is wide while others lose it when it changes direction or rolls at a high speed. In addition, the algorithms proposed for the detection of colors in RGB also lose their objectives when the object changes the color. But the proposed combination in this paper maintains contact with the object without losing it even if it changes direction or speed or the number of frame increases.

Moving Object Detection in Real-Time Using Stereo from a Mobile Platform

This paper presents a mobile object detection algorithm which performs with two consecutive stereo images. Like most motion detection methods, the proposed one is based on dense stereo matching and optical flow (OF) estimation. Noting that the main computational cost of existing methods is related to the estimation of OF, we propose to use a fast algorithm based on Lucas–Kanade paradigm. We then derive a comprehensive uncertainty model by taking into account all the estimation errors occurring during the process. In contrast with most previous works, we rigorously expand the error related to vision based ego-motion estimation. Finally, we present a comparative study of performance on the challenging KITTI dataset which demonstrates the effectiveness of the proposed approach.

Occupancy Grid Mapping Based on DSmT for Dynamic Environment Perception

Occupancy grid mapping is an important approach for intelligent vehicle environment perception. In this paper, an occupancy grid mapping approach in Dezert-Smarandache theory (DSmT) framework for the purpose of dynamic environment perception is proposed. To avoid the transformation of the local map from polar to Catersian coordinate, a different inverse sensor model in Cartesian coordinate for laser scanner was proposed. Two different combination rules in DSmT framework, Dempster’s rule of combination and PCR2, are implemented independently for global map update and mobile object detection. The performance of the two combination rules were compared by ways of simulation and experiment. According to the comparisons we find that both of the combination rules are capable of detecting mobile objects. And the former effectively filtered out the noise and make the detection robust, but the latter didn’t, suggesting that the former is more suitable for occupancy grid mapping. Static and mobile objects are extracted from the occupancy grid map using digital image processing technology. Full Text: PDF DOI: http://dx.doi.org/10.11591/ijra.v2i4.923

Hardware Implementation of FAST Algorithm for Mobile Applications

Simple inexpensive cameras are often built in small devices such as mobile phones or mp3 players. Besides the usual image recording, other ways of their use have been proposed which usually involve intensive image processing. In such processing, corner detection is often found as a preliminary operation. Many corner detection algorithms have been introduced, but due to their computational complexity very few are suitable for real-time applications. One of novel approaches to corner detection is the so called FAST algorithm which is specially optimized for speed. However, on simple and slow devices even this algorithm can be too slow and energy consuming when executed on the in-built processor. In this paper we present hardware implementation of FAST algorithm, capable of processing images at constant speed of one pixel per clock. The results showed that nearly forty times faster corner detection could be achieved on mobile object detection and localization application, if the existing software detector is replaced by our hardware module.

Detection of Mobile Objects for Outdoor Navigation Robots

Detection of Mobile Objects for Outdoor Navigation Robots

Detection of Mobile Objects by Mixture PDF Model for Mobile Robots

Detection of Mobile Objects by Mixture PDF Model for Mobile Robots

Mobile Object Detection from an Embedded camera: how to minimize the latency time?

AbstractThis paper presents a global approach devoted to the detection of Mobile Objects from images acquired by a single camera embedded on a vehicle or a robot. The general method is presented involving at first optical flow extraction from tracked interest points, then clustering between static points belonging to the background and mobile ones extracted on different mobile objects, and then the tracking procedure performed for every detected mobile object. First results obtained from a sequential implementation, have shown that the latency time was too important. Here two improvements are proposed: first, a probabilistic map is built in order to detect points in more probable regions where a mobile object could be found. Then sequential and parallel architectures proposed to integrate point detection, point tracking and point clustering, are analyzed with respect to the latency time. Finally experimental results are presented and discussed.

Detection of the Mobile Object with Camouflage Color Under Dynamic Background Based on Optical Flow

In order to realize the detection of the mobile object with camouflage color, a scheme based on optical flow model was put forward. Firstly, optical flow model was used to model the motion pattern of the object and the background. Secondly, the magnitude and the location of the optical flow were used to cluster the motion pattern, and the object detection result was obtained. At last, the location and scale of the object were used as the state variables, Kalman filter was used to improve the performance of the detection, and the final detection result was obtained. Experimental results show the algorithm can solve the mobile object detection satisfactorily.