Diabetic Retinopathy Detection Using Machine Learning
Volume-4 | Issue-1
Monocular Depth Estimation using a Multi-grid Attention-based Model
Volume-4 | Issue-3
Speedy Image Crowd Counting by Light Weight Convolutional Neural Network
Volume-3 | Issue-3
Construction of Efficient Smart Voting Machine with Liveness Detection Module
Volume-3 | Issue-3
An Economical Robotic Arm for Playing Chess Using Visual Servoing
Volume-2 | Issue-3
Triplet loss for Chromosome Classification
Volume-4 | Issue-1
Unstructured Noise Removal for Industrial Sensor Imaging Unit by Hybrid Adaptive Median Algorithm
Volume-3 | Issue-4
Real Time Sign Language Recognition and Speech Generation
Volume-2 | Issue-2
Analysis of Artificial Intelligence based Image Classification Techniques
Volume-2 | Issue-1
Design of ANN Based Machine Learning Method for Crop Prediction
Volume-3 | Issue-3
A REVIEW ON IOT BASED MEDICAL IMAGING TECHNOLOGY FOR HEALTHCARE APPLICATIONS
Volume-1 | Issue-1
COMPUTER VISION BASED TRAFFIC SIGN SENSING FOR SMART TRANSPORT
Volume-1 | Issue-1
Diabetic Retinopathy Detection Using Machine Learning
Volume-4 | Issue-1
Accurate Segmentation for Low Resolution Satellite images by Discriminative Generative Adversarial Network for Identifying Agriculture Fields
Volume-3 | Issue-4
Deep Learning based Handwriting Recognition with Adversarial Feature Deformation and Regularization
Volume-3 | Issue-4
State of Art Survey on Plant Leaf Disease Detection
Volume-4 | Issue-2
Optimal Compression of Remote Sensing Images Using Deep Learning during Transmission of Data
Volume-3 | Issue-4
OverFeat Network Algorithm for Fabric Defect Detection in Textile Industry
Volume-3 | Issue-4
VIRTUAL RESTORATION OF DAMAGED ARCHEOLOGICAL ARTIFACTS OBTAINED FROM EXPEDITIONS USING 3D VISUALIZATION
Volume-1 | Issue-2
Two-Stage Frame Extraction in Video Analysis for Accurate Prediction of Object Tracking by Improved Deep Learning
Volume-3 | Issue-4
Volume - 4 | Issue - 3 | september 2022
Published
12 August, 2022
With the increased use of depth information in computer vision, monocular depth estimation has been an emerging field of study. It is a challenging task where many deep convolutional neural network-based methods have been used for depth prediction. The problem with most of these approaches is that they use a repeated combination of max-pooling and striding in an encoder, which reduces spatial resolution. In addition, these approaches use information from all the channels directly from the encoder, which is prone to noise. Addressing these issues, we present a multigrid attention-based densenet-161 model. It consists of a multigrid densenet-161 encoder that increases the spatial resolution and an attention-based decoder to select the important information from low-level features. We achieved absolute relative error (Absrel) of 0.109 and 0.0724 on NYU v2 and KITTI, dataset respectively. Our proposed method exceeded most evaluation measures with fewer parameters compared to the state-of-the-art on standard benchmark datasets. We produce a dense depth map from a single RGB image which can be used to create a dense point cloud. The anticipated depth map is accurate and smooth, which can be used in several applications.
KeywordsConvolutional Neural Network (CNN) depth estimation dilation rate multigrid attention mechanism depth map
Full Article PDF Download Article PDF