scholarly journals Investigasi Pengaruh Step Training pada Metode Single Shot Multibox Detector untuk Marker dalam Teknologi Augmented Reality

2020 ◽  
Vol 12 (1) ◽  
pp. 1
Author(s):  
Vivian Alfionita Sutama ◽  
Suryo Adhi Wibowo ◽  
Rissa Rahmania
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Augmented Reality ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Transfer Learning ◽  
Learning Rate ◽  
Batch Size ◽  
Single Shot

Nowadays, Artificial Intelligence is one of the most developing technology, especially on Augmented Reality (AR). AR is a technology which connected between real world and virtual in a real time that allows user to interact directly and display it in 3D. AR technology has two methods, that are AR based on marker and AR based on markerless. However, AR based on marker need an object detection system which has high performance as an interaction tools between user and the device. Single shot multibox detector (SSD) is an object detection algorithm that has fast learning computation and good performance. This method is affected by some parameters like number of epoch, learning rate, batch size, step training, etc. However, to create a good system it took a long process such as taking dataset, labelling process, then training and testing models to gain the best performance. In this experiment, we analyze SSD method in AR technology using inception architecture as pre-trained Convolutional neural network (CNN), and then do transfer learning to minimize amount training time. The configuration that used is the number of step training. The result of this experiment gets the best accuracy in 70.17%. Then, the best performance is used as an object detection model for marker’s AR technology.Abstrak Saat ini, Artificial intelligence merupakan teknologi yang sedang berkembang pesat. Salah satunya adalah teknologi Augmented Reality (AR). AR adalah teknologi yang menggabungkan dunia nyata dengan virtual secara real-time dengan interaksi pengguna secara langsung dan menampilkannya dalam bentuk 3D. Teknologi AR ini memiliki dua metode yaitu dengan marker dan markerless. Dalam perkembangannya, AR berbasis marker membutuhkan sistem deteksi objek yang memiliki performa tinggi sebagai alat interaksi antara pengguna dengan perangkatnya. Single shot multibox detector (SSD) merupakan algoritma deteksi objek yang memiliki komputasi pembelajaran dan kinerja yang baik. Metode ini dipengaruhi oleh beberapa parameter seperti jumlah lapisan konvolusi, epoch, learning rate, jumlah batch, step training, dll. Namun, dalam mengimplementasikannya diperlukan proses yang cukup panjang seperti, pengambilan dataset, proses pelabelan, proses pelatihan menggunakan metode SSD, dan melakukan pengujian terhadap beberapa model untuk mencari perfomansi paling baik. Dalam percobaan ini, kami melakukan analisis terhadap metode SSD pada teknologi AR menggunakan arsitektur Inception sebagai pre-trained Convolutional neural network (CNN), kemudian dilakukan transfer learning untuk memperkecil jumlah kelas data pelatihan dan waktu pelatihan data. Konfigurasi yang digunakan berupa jumlah step pada pelatihan. Hasil dari penilitian ini menunjukan akurasi terbaik sebesar 70,17%. Kemudian, perfomansi terbaik digunakan sebagai model deteksi objek untuk marker pada teknologi AR.

scholarly journals Implementation of an Obstacle Recognition System for the Blind

2019 ◽  
Vol 10 (1) ◽  
pp. 282 ◽  
Author(s):  
Soobin Ou ◽  
Huijin Park ◽  
Jongwoo Lee
Keyword(s):  
Neural Network ◽  
Remote Control ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Support Systems ◽  
Acoustic Signals ◽  
Recognition System ◽  
Single Shot ◽  
Program Interface

The blind encounter commuting risks, such as failing to recognize and avoid obstacles while walking, but protective support systems are lacking. Acoustic signals at crosswalk lights are activated by button or remote control; however, these signals are difficult to operate and not always available (i.e., broken). Bollards are posts installed for pedestrian safety, but they can create dangerous situations in that the blind cannot see them. Therefore, we proposed an obstacle recognition system to assist the blind in walking safely outdoors; this system can recognize and guide the blind through two obstacles (crosswalk lights and bollards) with image training from the Google Object Detection application program interface (API) based on TensorFlow. The recognized results notify the blind through voice guidance playback in real time. The single shot multibox detector (SSD) MobileNet and faster region-convolutional neural network (R-CNN) models were applied to evaluate the obstacle recognition system; the latter model demonstrated better performance. Crosswalk lights were evaluated and found to perform better during the day than night. They were also analyzed to determine if a client could cross at a crosswalk, while the locations of bollards were analyzed by algorithms to guide the client by voice guidance.

Real-Time 3D object detection using improved convolutional neural network based on image-driven point cloud

2021 ◽  
Vol 14 ◽  
Author(s):  
Zhiyong Gao ◽  
Jianhong Xiang
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Point Cloud ◽  
Point Clouds ◽  
3D Point Cloud ◽  
3D Object ◽  
3D Object Detection ◽  
Instance Segmentation

Background: While detecting the object directly from the 3D point cloud, the natural 3D patterns and invariance of 3D data are often obscure. Objective: In this work, we aimed at studying the 3D object detection from discrete, disordered and sparse 3D point clouds. Methods: The CNN is composed of the frustum sequence module, 3D instance segmentation module S-NET, 3D point cloud transformation module T-NET, and 3D boundary box estimation module E-NET. The search space of the object is determined by the frustum sequence module. The instance segmentation of the point cloud is performed by the 3D instance segmentation module. The 3D coordinates of the object are confirmed by the transformation module and the 3D bounding box estimation module. Results: Evaluated on KITTI benchmark dataset, our method outperforms the state of the art by remarkable margins while having real-time capability. Conclusion: We achieve real-time 3D object detection by proposing an improved convolutional neural network (CNN) based on image-driven point clouds.

scholarly journals Design of a Scalable and Fast YOLO for Edge-Computing Devices

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6779
Author(s):  
Byung-Gil Han ◽  
Joon-Goo Lee ◽  
Kil-Taek Lim ◽  
Doo-Hyun Choi
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Processing Speed ◽  
Edge Computing ◽  
Light Weight ◽  
Detection Technology ◽  
Accuracy Performance ◽  
Speed And Accuracy

With the increase in research cases of the application of a convolutional neural network (CNN)-based object detection technology, studies on the light-weight CNN models that can be performed in real time on the edge-computing devices are also increasing. This paper proposed scalable convolutional blocks that can be easily designed CNN networks of You Only Look Once (YOLO) detector which have the balanced processing speed and accuracy of the target edge-computing devices considering different performances by exchanging the proposed blocks simply. The maximum number of kernels of the convolutional layer was determined through simple but intuitive speed comparison tests for three edge-computing devices to be considered. The scalable convolutional blocks were designed in consideration of the limited maximum number of kernels to detect objects in real time on these edge-computing devices. Three scalable and fast YOLO detectors (SF-YOLO) which designed using the proposed scalable convolutional blocks compared the processing speed and accuracy with several conventional light-weight YOLO detectors on the edge-computing devices. When compared with YOLOv3-tiny, SF-YOLO was seen to be 2 times faster than the previous processing speed but with the same accuracy as YOLOv3-tiny, and also, a 48% improved processing speed than the YOLOv3-tiny-PRN which is the processing speed improvement model. Also, even in the large SF-YOLO model that focuses on the accuracy performance, it achieved a 10% faster processing speed with better accuracy of 40.4% [email protected] in the MS COCO dataset than YOLOv4-tiny model.

scholarly journals Health Monitoring for Balancing Tail Ropes of a Hoisting System Using a Convolutional Neural Network

2018 ◽  
Vol 8 (8) ◽  
pp. 1346 ◽  
Author(s):  
Ping Zhou ◽  
Gongbo Zhou ◽  
Zhencai Zhu ◽  
Chaoquan Tang ◽  
Zhenzhi He ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Health Monitoring ◽  
Nearest Neighbor ◽  
Back Propagation ◽  
Feature Space ◽  
Batch Size ◽  
K Nearest Neighbor ◽  
Hoisting System

With the arrival of the big data era, it has become possible to apply deep learning to the health monitoring of mine production. In this paper, a convolutional neural network (CNN)-based method is proposed to monitor the health condition of the balancing tail ropes (BTRs) of the hoisting system, in which the feature of the BTR image is adaptively extracted using a CNN. This method can automatically detect various BTR faults in real-time, including disproportional spacing, twisted rope, broken strand and broken rope faults. Firstly, a CNN structure is proposed, and regularization technology is adopted to prevent overfitting. Then, a method of image dataset description and establishment that can cover the entire feature space of overhanging BTRs is put forward. Finally, the CNN and two traditional data mining algorithms, namely, k-nearest neighbor (KNN) and an artificial neural network with back propagation (ANN-BP), are adopted to train and test the established dataset, and the influence of hyperparameters on the network diagnostic accuracy is investigated experimentally. The experimental results showed that the CNN could effectively avoid complex steps such as manual feature extraction, that the learning rate and batch-size strongly affected the accuracy and training efficiency, and that the fault diagnosis accuracy of CNN was 100%, which was higher than that of KNN and ANN-BP. Therefore, the proposed CNN with high accuracy, real-time functioning and generalization performance is suitable for application in the health monitoring of hoisting system BTRs.

scholarly journals Detection of Tomato Plant Diseases Using Deep Convolutional Neural Network

2020 ◽  
pp. 464-465
Author(s):  
Vijayaganth V ◽  
Naveenkumar M ◽  
Mohan M
Keyword(s):  
Neural Network ◽  
Early Diagnosis ◽  
Convolutional Neural Network ◽  
Tomato Plant ◽  
Learning Rate ◽  
Deep Convolutional Neural Network ◽  
Plant Diseases ◽  
Batch Size ◽  
Diagnosis Of Diseases

The disease in tomato leaves affects the quality and quantity of the crops. To overcome this problem an early diagnosis of diseases will benefit the farmers. This work uses PlantVillage dataset of 9 tomato leaves and fed to AlexNet and VGG16. It focuses on accuracy of the model by using hyperparameters like batch size, learning rate and optimizer.

scholarly journals COMPARISON INTENT RECOGNITION ON FOOD DELIVERY SERVICE COMPLAINT IN TWITTER WITH RECURRENT AND CONVOLUTIONAL NEURAL NETWORK

2020 ◽  
Vol 5 (1) ◽  
Author(s):  
Irfan Nasrullah ◽  
Rila Mandala
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Food Delivery ◽  
Learning Rate ◽  
Batch Size ◽  
Optimal Result ◽  
Intent Recognition ◽  
Delivery Service ◽  
Customer Relation Management ◽  
Large Fluctuations

In this research, the case of intent classification for Customer Relation Management (CRM) how to handle complaints as a domain to be followed up, where datasets are extracted from the conversation on Twitter. The research objectives support three key findings to comparing the CNNs and BRNNs model to intent recognition by vectorization text: (1) Which architecture performs better (accuracy) depends on how important it is to semantically understand the whole sequence and (2) Learning rate changes performance relatively smoothly, while the optimal result iterated by change hidden size and batch size result in large fluctuations. (3) Last, how word vectorization is able to define sub-domain of the complaints by word vector classification.

Detecting Safe and Not Safe Driving Actions using Convolutional Neural Network

2021 ◽  
pp. 372-378
Author(s):  
Saurabh Takle ◽  
Shubham Desai ◽  
Sahil Mirgal ◽  
Ichhanshu Jaiswal
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Transfer Learning ◽  
Mobile Phones ◽  
State Farm ◽  
Safe Driving ◽  
Cognitive Distraction ◽  
Video Feed

<p>The main cause of accidents is due to Manual, Visual or Cognitive distraction out of these three Manual distractions are concerned with various activities where “driver’s hands are off the wheel”. Such distractions include talking or texting using mobile phones, eating and drinking, talking to passengers in the vehicle, adjusting the radio, makeup, etc. To solve the problem of manual distraction, the Convolutional Neural Network (CNN) model of ResNet-50 using transfer learning with 23,587,712 parameters was used. The dataset used is from State Farm Distracted Driver Detection Dataset. The training accuracy is 97.27% and validation accuracy is 55%. Further the model works on detecting real-time distractions on a video feed for this purpose the system uses OpenCV and the model is integrated with the frontend using the flask.</p>

scholarly journals Wearable Airbag System for Real-Time Bicycle Rider Accident Recognition by Orthogonal Convolutional Neural Network (O-CNN) Model

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1423
Author(s):  
Joo Woo ◽  
So-Hyeon Jo ◽  
Gi-Sig Byun ◽  
Baek-Soon Kwon ◽  
Jae-Hoon Jeong
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Neck Injuries ◽  
Judgment Accuracy ◽  
Time Motion ◽  
Motion Condition ◽  
Bicycle Rider ◽  
Accident Conditions

As demand for bicycles increases, bicycle-related accidents are on the rise. There are many items such as helmets and racing suits for bicycles, but many people do not wear helmets even if they are the most basic safety protection. To protect the rider from accidents, technology is needed to measure the rider’s motion condition in real time, determine whether an accident has occurred, and cope with the accident. This paper describes an artificial intelligence airbag. The artificial intelligence airbag is a system that measures real-time motion conditions of a bicycle rider using a six-axis sensor and judges accidents with artificial intelligence to prevent neck injuries. The MPU 6050 is used to understand changes in the rider’s movement in normal and accident conditions. The angle is determined by using the measured data and artificial intelligence to determine whether an accident happened or not by analyzing acceleration and angle. In this paper, similar methods of artificial intelligence (NN, PNN, CNN, PNN-CNN) to are compared to the orthogonal convolutional neural network (O-CNN) method in terms of the performance of judgment accuracy for accident situations. The artificial neural networks were applied to the airbag system and verified the reliability and judgment in advance.

Sign in / Sign up

Export Citation Format

Share Document