Bipul Neupane

University of Melbourne, Department of Infrastructure Engineering,, Graduate Student

Kathmandu University, Department of Civil and Geomatics Engineering, Undergraduate

Thammasat University, Sirindhorn International Institute of Technology, Researcher

Followers

Following

Public Views

Bipul Neupane was born in Kathmandu, Nepal in 1993. He received his B.E. in Geomatics Engineering from Kathmandu University, Nepal in 2015 and an M.S. in Engineering and Technology from Sirindhorn International Institute of Technology (SIIT), Thammasat University, Thailand in 2019. He is currently a Ph.D. fellow at the University of Melbourne (UoM), Australia. He is supported by the University of Melbourne for his Ph.D. research and is awarded by Melbourne Research Scholarship. Before coming to UoM, and worked as a Researcher at SIIT, Thammasat University, where he carries out several research works related to location intelligence using earth observation in urban and agricultural applications. His research interests include digital image processing and object classification using sensing technologies for public safety. His past work includes being GIS/M\&E Officer for location intelligence in the health sector and land-use planning services.
Supervisors: Jagannath Aryal, Teerayut Horanont, and Nguyen Dy Hung
Address: 6.029 - 700 Swanston St, Carlton VIC 3053

less

Sudeep Varshney

Teena Sharma

Khaled R Ahmed

Southern Illinois University at Carbondale

Jamuna S Murthy

Minar Mahmud Rafi (181014047)

Williamjeet Singh

Punjabi University Patiala

BINUS University

Interests

Uploads

Papers by Bipul Neupane

Robust and Scalable Real-Time Vehicle Classification and Tracking: A Case Study of Thailand

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

An accurate detection, classification, and tracking of vehicles are highly important for intellig... more An accurate detection, classification, and tracking of vehicles are highly important for intelligent transport systems (ITS) and road maintenance. In recent years, the deep learning (DL)-based approach is highly regarded for real-time vehicle classification from surveillance cameras. However, the practical implementation of such an approach is affected by the adverse lighting conditions and positioning of the cameras. In this research, we develop a DL-based method for near real-time multi-vehicle counting, classifying, and tracking on individual lanes of the road. First, we train a DL network of the You Only Look Once (YOLO) family on a custom dataset that we have curated. The dataset consists of nearly 30000 training samples to classify the vehicles into seven classes, which is more than in the existing benchmark datasets. Second, we fine-tune the trained model into another small dataset collected from the surveillance cameras that are used during the implementation process. Third, we connect the trained model to a tracking algorithm that we have developed to produce a per-lane report with the calculation of the speed and mobility of the vehicles. We test the robustness of the system on different faces of the vehicles and in adverse lighting conditions. The overall accuracy (OA) of classification ranges from 91% to 99% in four faces of vehicles (back, front, driver side, and passenger side). Similarly, in an experiment on adverse lighting conditions, OA of 93.7% and 99.6% is observed in a noisy and clear lighting conditions respectively. The implications of these results will assist in road maintenance with spatial information management and sensing for intelligent transport planning.

Download

Building Footprint Segmentation Using Transfer Learning: A Case Study of the City of Melbourne

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Earth observation data including very high-resolution (VHR) imagery from satellites and unmanned ... more Earth observation data including very high-resolution (VHR) imagery from satellites and unmanned aerial vehicles (UAVs) are the primary sources for highly accurate building footprint segmentation and extraction. However, with the increase in spatial resolution, smaller objects are prominently visible in the images, and using intelligent approaches like deep learning (DL) suffers from several problems. In this paper, we outline four prominent problems while using DL-based methods (P1, P2, P3, and P4)): (P1) lack of contextual features, (P2) requirement of a large training dataset, (P3) domain-shift problem, and (P4) computational expense. In tackling P1, we modify a commonly used DL architecture called U-Net to increase the contextual feature information. Likewise, for P2 and P3, we use transfer learning to fine-tune the DL model on a smaller dataset utilising the knowledge previously gained from a larger dataset. For P4, we study the trade-off between the network's performance and computational expense with reduced training parameters and optimum learning rates. Our experiments on a case study from the City of Melbourne show that the modified U-Net is highly robust than the original U-Net and SegNet, and the dataset we develop is significantly more robust than an existing benchmark dataset. Furthermore, the overall method of fine-tuning the modified U-Net reduces the number of training parameters by 300 times and training time by 2.5 times while preserving the precision of segmentation.

Download

Object vs Pixel-based Flood/Drought Detection in Paddy Fields using Deep Learning

2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)

Real-Time Vehicle Classification and Tracking Using a Transfer Learning-Improved Deep Learning Network

Sensors

Accurate vehicle classification and tracking are increasingly important subjects for intelligent ... more Accurate vehicle classification and tracking are increasingly important subjects for intelligent transport systems (ITSs) and for planning that utilizes precise location intelligence. Deep learning (DL) and computer vision are intelligent methods; however, accurate real-time classification and tracking come with problems. We tackle three prominent problems (P1, P2, and P3): the need for a large training dataset (P1), the domain-shift problem (P2), and coupling a real-time multi-vehicle tracking algorithm with DL (P3). To address P1, we created a training dataset of nearly 30,000 samples from existing cameras with seven classes of vehicles. To tackle P2, we trained and applied transfer learning-based fine-tuning on several state-of-the-art YOLO (You Only Look Once) networks. For P3, we propose a multi-vehicle tracking algorithm that obtains the per-lane count, classification, and speed of vehicles in real time. The experiments showed that accuracy doubled after fine-tuning (71% vs. u...

Download

Deep Learning-Based Semantic Segmentation of Urban Features in Satellite Images: A Review and Meta-Analysis

Remote Sensing

Availability of very high-resolution remote sensing images and advancement of deep learning metho... more Availability of very high-resolution remote sensing images and advancement of deep learning methods have shifted the paradigm of image classification from pixel-based and object-based methods to deep learning-based semantic segmentation. This shift demands a structured analysis and revision of the current status on the research domain of deep learning-based semantic segmentation. The focus of this paper is on urban remote sensing images. We review and perform a meta-analysis to juxtapose recent papers in terms of research problems, data source, data preparation methods including pre-processing and augmentation techniques, training details on architectures, backbones, frameworks, optimizers, loss functions and other hyper-parameters and performance comparison. Our detailed review and meta-analysis show that deep learning not only outperforms traditional methods in terms of accuracy, but also addresses several challenges previously faced. Further, we provide future directions of resea...

Download

Deep learning based banana plant detection and counting using high-resolution red-green-blue (RGB) images collected from unmanned aerial vehicle (UAV)

PLOS ONE

The production of banana-one of the highly consumed fruits-is highly affected due to loss of cert... more The production of banana-one of the highly consumed fruits-is highly affected due to loss of certain number of banana plants in an early phase of vegetation. This affects the ability of farmers to forecast and estimate the production of banana. In this paper, we propose a deep learning (DL) based method to precisely detect and count banana plants on a farm exclusive of other plants, using high resolution RGB aerial images collected from Unmanned Aerial Vehicle (UAV). An attempt to detect the plants on the normal RGB images resulted less than 78.8% recall for our sample images of a commercial banana farm in Thailand. To improve this result, we use three image processing methods-Linear Contrast Stretch, Synthetic Color Transform and Triangular Greenness Index-to enhance the vegetative properties of orthomosaic, generating multiple variants of orthomosaic. Then we separately train a parameter-optimized Convolutional Neural Network (CNN) on manually interpreted banana plant samples seen on each image variants, to produce multiple results of detection on our region of interest. 96.4%, 85.1% and 75.8% of plants were correctly detected on three of our dataset collected from multiple altitude of 40, 50 and 60 meters, of same farm. Further discussion on results obtained from combination of multiple altitude variants are also discussed later in the research, in an attempt to find better altitude combination for data collection from UAV for the detection of banana plants. The results showed that merging the detection results of 40 and 50 meter dataset could detect the plants missed by each other, increasing recall upto 99%.

Download

Weather Scenario Generation Game

2018 Thirteenth International Conference on Knowledge, Information and Creativity Support Systems (KICSS), 2018

The unavailability of seasonal weather data at the simulation time (often beginning of a growth s... more The unavailability of seasonal weather data at the simulation time (often beginning of a growth season) forces decision makers in crop growth assessment to consider multiple weather scenarios, which are often generated from longtime observed data. Ironically these scenarios immediately become “outdated” as soon as the season begins, because they are always different from newly observed data. In this paper, we investigate this dilemma and in particular address three questions: determination of most successful scenario, classification of scenarios into fresh and stale, and generation of a new scenario from fresh scenarios. Algorithms to solve these questions are given as strategies for prediction games of weather generators. We also elaborate on the applications of our results in networking existing weather generation web services.

An Open-Source UAV Image Processing Web Service for Crop Health Monitoring

2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI), 2019

Unmanned Aerial Vehicle (UAV) photogrammetry has allowed to monitor crop growth/health and remote... more Unmanned Aerial Vehicle (UAV) photogrammetry has allowed to monitor crop growth/health and remotely estimate biomass through calculation of Vegetation Indices (VI). However, some of the indices require costly sensors, and the process of generating VI maps from UAV images also requires commercial off-the-shelf software packages. This study uses existing open-source tools and methods to develop an algorithm for a web-service that can create orthophotos, canopy height model and VI's for red-green-blue (RGB) images collected from UAV. We also discuss on ways to balance between the processing speed and quality of outputs, and further compare them to the outputs of an existing state-of-the-art commercial service.

Real-time Drowsiness and Distraction Detection using Computer Vision and Deep Learning

Proceedings of the 11th International Conference on Advances in Information Technology

Automated analysis of driver's attention to driving is crucial to reduce traffic accidents. R... more Automated analysis of driver's attention to driving is crucial to reduce traffic accidents. Real-time detection of initial signs of drowsiness or distraction of driver has yet not been most reliable. This study is therefore oriented towards improving this problem by strategically detecting some of the necessary parameters like closing of eye, yawning, and head orientation of driver. We use deep neural network (DNN) to extract face and facial landmarks, followed by calculation of Eye Aspect Ratio (EAR), Mouth Aspect Ratio (MAR) and pose estimation using 3D location and intrinsic parameters to detect whether or not driver is focused into driving. Our experimental results shows better real-time performance than traditional methods in many aspects, which is why we further deploy the algorithm as a mobile application.

Deep learning based banana plant detection and counting using high-resolution red-green-blue (RGB) images collected from unmanned aerial vehicle (UAV)

PLOS ONE, Oct 17, 2019

Download

Useful AI applications in agriculture: aggregation of machine learning techniques for weather forecasting and banana plant counting

Modern problems in agricultural seek methods to increase the convenience, reliability accuracy an... more Modern problems in agricultural seek methods to increase the convenience, reliability accuracy and at the same time, cost efficacy in precision farming. To exploit the global research gaps in sustainable agriculture, this thesis organizes three different works committed to provide solutions to three modern agricultural problems: reliable crop modeling, accurate crop counting and cost-effective crop health monitoring. As strategic solutions, this study proposes the use of emerging advancements on recent artificial intelligence technologies, weather forecasting, web-services, aerial imagery and digital image processing to connect the crucial cores of sustainable agriculture visions. The outputs of this work is targeted help decision makers, and specially the farmers themselves, to increase the productivity of farms for better yield, and to draw young people to the farms to meet the global hunger of 21st century with sustainability in life support and food security. The unavailability ...

Robust and Scalable Real-Time Vehicle Classification and Tracking: A Case Study of Thailand

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Download

Building Footprint Segmentation Using Transfer Learning: A Case Study of the City of Melbourne

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Download

Object vs Pixel-based Flood/Drought Detection in Paddy Fields using Deep Learning

2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)

Real-Time Vehicle Classification and Tracking Using a Transfer Learning-Improved Deep Learning Network

Sensors

Download

Deep Learning-Based Semantic Segmentation of Urban Features in Satellite Images: A Review and Meta-Analysis

Remote Sensing

Download

Deep learning based banana plant detection and counting using high-resolution red-green-blue (RGB) images collected from unmanned aerial vehicle (UAV)

PLOS ONE

Download

Weather Scenario Generation Game

2018 Thirteenth International Conference on Knowledge, Information and Creativity Support Systems (KICSS), 2018

An Open-Source UAV Image Processing Web Service for Crop Health Monitoring

2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI), 2019

Real-time Drowsiness and Distraction Detection using Computer Vision and Deep Learning

Proceedings of the 11th International Conference on Advances in Information Technology

Deep learning based banana plant detection and counting using high-resolution red-green-blue (RGB) images collected from unmanned aerial vehicle (UAV)

PLOS ONE, Oct 17, 2019

Download

Useful AI applications in agriculture: aggregation of machine learning techniques for weather forecasting and banana plant counting

Bipul Neupane

Uploads

Papers by Bipul Neupane

Log In