Deep vision networks for real-time robotic grasp detection

Grasping has always been a great challenge for robots due to its lack of the ability to well understand the perceived sensing data. In this work, we propose an end-to-end deep vision network model to predict possible good grasps from real-world images in real time. In order to accelerate the speed of the grasp detection, reference rectangles are designed to suggest potential grasp locations and then refined to indicate robotic grasps in the image. With the proposed model, the graspable scores for each location in the image and the corresponding predicted grasp rectangles can be obtained in real time at a rate of 80 frames per second on a graphic processing unit. The model is evaluated on a real robot-collected data set and different reference rectangle settings are compared to yield the best detection performance. The experimental results demonstrate that the proposed approach can assist the robot to learn the graspable part of the object from the image in a fast manner.

Download Full-text

Real-time radar signal processing using GPGPU (general-purpose graphic processing unit)

10.1117/12.2222282 ◽

2016 ◽

Cited By ~ 1

Author(s):

Fanxing Kong ◽

Yan Rockee Zhang ◽

Jingxiao Cai ◽

Robert D. Palmer

Keyword(s):

Signal Processing ◽

Real Time ◽

Graphic Processing Unit ◽

General Purpose ◽

Radar Signal ◽

Radar Signal Processing ◽

Processing Unit ◽

Graphic Processing

Download Full-text

Partially Coherent Beam Real-Time Generation Method Accelerated by Graphic Processing Unit

ACTA PHOTONICA SINICA ◽

10.3788/gzxb20164503.0310001 ◽

2016 ◽

Vol 45 (3) ◽

pp. 310001 ◽

Cited By ~ 1

Author(s):

倪小龙 NI Xiao-long ◽

刘智 LIU Zhi ◽

姜会林 JIANG Hui-lin ◽

陈纯毅 CHEN Chun-yi ◽

刘艺 LIU Yi ◽

...

Keyword(s):

Real Time ◽

Graphic Processing Unit ◽

Coherent Beam ◽

Processing Unit ◽

Partially Coherent ◽

Graphic Processing

Download Full-text

Learning in a neural network model in real time using real world stimuli

Neurocomputing ◽

10.1016/s0925-2312(01)00357-5 ◽

2001 ◽

Vol 38-40 ◽

pp. 859-865 ◽

Cited By ~ 1

Author(s):

Manuel A. Sánchez-Montañés ◽

Peter König ◽

Paul F.M.J. Verschure

Keyword(s):

Neural Network ◽

Real Time ◽

Network Model ◽

Neural Network Model ◽

Real World

Download Full-text

Vision Sensor-Based Real-Time Fire Detection in Resource-Constrained IoT Environments

Computational Intelligence and Neuroscience ◽

10.1155/2021/5195508 ◽

2021 ◽

Vol 2021 ◽

pp. 1-15

Author(s):

Hikmat Yar ◽

Tanveer Hussain ◽

Zulfiqar Ahmad Khan ◽

Deepika Koundal ◽

Mi Young Lee ◽

...

Keyword(s):

Real Time ◽

Real World ◽

False Positive Rate ◽

Fire Detection ◽

Resource Constrained ◽

Training Time ◽

Input Size ◽

Proposed Model ◽

High Level ◽

Early Fire Detection

Fire detection and management is very important to prevent social, ecological, and economic damages. However, achieving real-time fire detection with higher accuracy in an IoT environment is a challenging task due to limited storage, transmission, and computation resources. To overcome these challenges, early fire detection and automatic response are very significant. Therefore, we develop a novel framework based on a lightweight convolutional neural network (CNN), requiring less training time, and it is applicable over resource-constrained devices. The internal architecture of the proposed model is inspired by the block-wise VGG16 architecture with a significantly reduced number of parameters, input size, inference time, and comparatively higher accuracy for early fire detection. In the proposed model, small-size uniform convolutional filters are employed that are specifically designed to capture fine details of input fire images with a sequentially increasing number of channels to aid effective feature extraction. The proposed model is evaluated on two datasets such as a benchmark Foggia’s dataset and our newly created small-scaled fire detection dataset with extremely challenging real-world images containing a high-level of diversity. Experimental results conducted on both datasets reveal the better performance of the proposed model compared to state-of-the-art in terms of accuracy, false-positive rate, model size, and running time, which indicates its robustness and feasible installation in real-world scenarios.

Download Full-text

Traffic Sign Classification Using Convolutional Neural Network

International Journal of Scientific Research in Computer Science Engineering and Information Technology ◽

10.32628/cseit217545 ◽

2021 ◽

pp. 01-10

Author(s):

Pranav Kale ◽

Mayuresh Panchpor ◽

Saloni Dingore ◽

Saloni Gaikwad ◽

Prof. Dr. Laxmi Bewoor

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Real Time ◽

Autonomous Driving ◽

Time Data ◽

Traffic Sign ◽

Real World Data ◽

Data Set ◽

Proposed Model ◽

Validation Set

In today's world, deep learning fields are getting boosted with increasing speed. Lot of innovations and different algorithms are being developed. In field of computer vision, related to autonomous driving sector, traffic signs play an important role to provide real time data of an environment. Different algorithms were developed to classify these Signs. But performance still needs to improve for real time environment. Even the computational power required to train such model is high. In this paper, Convolutional Neural Network model is used to Classify Traffic Sign. The experiments are conducted on a real-world data set with images and videos captured from ordinary car driving as well as on GTSRB dataset [15] available on Kaggle. This proposed model is able to outperform previous models and resulted with accuracy of 99.6% on validation set. This idea has been granted Innovation Patent by Australian IP to Authors of this Research Paper. [24]

Download Full-text