P. Shunmuga Perumal

@vit.ac.in

Assistant Professor, Department of IT
Vellore Institute of Technology, Vellore.

P. Shunmuga Perumal


                  Download Compact PDF  
https://researchid.co/shansuja2022

EDUCATION

B.E. (IT), M.E. (VLSI Design), Ph.D

RESEARCH INTERESTS

Autonomous Vehicles, autonomous robots, deep learning models, perception systems, Internet of Things, Computer networks.
18

Scopus Publications

276

Scholar Citations

8

Scholar h-index

7

Scholar i10-index

Scopus Publications

  • 5G-enabled interactive sugarcane protection networks for farmers and experts: Custom sugarcane dataset trained SPIDCNet for under-canopy sugarcane insect and disease detection
    Maheshkumar S, P Shunmuga Perumal, R Viswanathan, Chandramani Raj, Mohammad SaqibDar, et al.
    Smart Agricultural Technology, 2026
  • An unmanned aerial vehicle captured dataset for railroad segmentation and obstacle detection
    Rampriya R. S., Taher Al-Shehari, Sabari Nathan, Jenefa A., Suganya R., et al.
    Scientific Data, 2024
    Safety is crucial in the railway industry because railways transport millions of passengers and employees daily, making it paramount to prevent injuries and fatalities. In order to guarantee passenger safety, computer vision, unmanned aerial vehicles (UAV), and artificial intelligence will be essential tools in the near future for routinely evaluating the railway environment. An unmanned aerial vehicle captured dataset for railroad segmentation and obstacle detection (UAV-RSOD) comprises high-resolution images captured by UAVs over various obstacles within railroad scenes, enabling automatic railroad extraction and obstacle detection. The dataset includes 315 raw images, along with 630 labeled and 630 masked images for railroad semantic segmentation. The dataset consists of 315 original images captured by the UAV for object detection and obstacle detection. To increase dataset diversity for training purposes, we applied data augmentation techniques, which expanded the dataset to 2002 augmented and annotated images for obstacle detection cover six different classes of obstacles on railroad lines. Additionally, we provide the original 315 images along with a script for augmentation, allowing users to generate their own augmented data as needed, offering a more sustainable and customizable option. Each image in the dataset is accurately annotated with bounding boxes and labeled under six categories, including person, boulder, barrel, branch, jerry can, and iron rod. This comprehensive classification and detailed annotation make the dataset an essential tool for researchers and developers working on computer vision applications in the railroad domain.
  • Lightweight railroad semantic segmentation network and distance estimation for railroad Unmanned aerial vehicle images
    R.S. Rampriya, Sabari Nathan, R. Suganya, Sahaya Beni Prathiba, P. Shunmuga Perumal, et al.
    Engineering Applications of Artificial Intelligence, 2024
  • Sugarcane Internode Dataset: SIDCNet for Detection and Counting of Sugarcane Internodes for Precision Agriculture
    Maheshkumar S, P. Shunmuga Perumal
    Cins 2024 2nd International Conference on Computational Intelligence and Network Systems, 2024
    This research proposes a custom sugarcane internode dataset. Sugarcane internode count analysis is a crucial parameter that helps experts analyse the cane health status, quality, and quantity of the juice to measure yield and productivity. The conventional sugarcane internode counting methods are done manually, which is inefficient as it consumes a lot of workforce, time, and cost. Also, the accuracy of the manual sugarcane counting methods is not guaranteed because of the sugarcane field ergonomics and lack of skilled workers. The overhead of the manual counting methods motivated us to develop a novel Sugarcane Internode Detection and Counting Network (SIDCNet). Two versions of SIDCNet namely SIDCNet_Vl and SIDCNet_V2 are experimented in this work. This work collected a custom sugarcane internode dataset from Vellore sugarcane fields in Tamil Nadu, India, to improve the model performance. The proposed model utilises YOLOv4 as the base, where the pre-trained weights are retrained using both online and VIT's custom sugarcane internode dataset with 6682 images. The SIDCNet_ V2 model demonstrated a notable average accuracy of 95.37% in detecting and counting sugarcane internodes while exhibiting minimal false positives. The proposed model's performance was tested on real-time images and videos captured by a ground rover platform. Further, the inference results produced by the SIDCNets were compared with the ground truth values to ensure accuracy. The experimental results reveal that the proposed model can automate the sugarcane internode detection and counting process, which helps experts monitor the sugarcane internode growth and status throughout the crop period, thereby improving sugarcane productivity. In addition to the model experimentation on the custom sugarcane internode dataset, this research article also intends to reveal the methodologies and challenges of the custom sugarcane dataset collection process.
  • Intelligent Driver Guidance Dashboard Framework to Prevent Road Accidents in Poor Visibility Conditions
    P. Shunmuga Perumal, Mamlesh VA, Rahul L, Shivanshu Tiwari
    Cins 2024 2nd International Conference on Computational Intelligence and Network Systems, 2024
    Road accidents pose a considerable global public concern, particularly on highways and rural roads. Road accidents contribute to half of all traffic fatalities. In India, low visibility conditions accounted for 7.1% of the 2022 road accidents totalling 4,61,312 [1]. Road accidents are caused by various factors, including fog, rain, low light conditions, poor road maintenance, traffic rule violations, and driving under the influence. Among these factors, low-light conditions challenge even skilled drivers, as they struggle significantly to detect and avoid on-road obstacles while driving. Existing driver assistance systems have limitations under poor visibility conditions, often lacking accurate obstacle information. In this paper, an Intelligent driver guidance dashboard (IDGDB) is proposed to assist drivers in avoiding on-road obstacles such as four-wheelers, two-wheelers, pedestrians, traffic light poles, and trees under poor visibility conditions caused by low-light, and opposite headlight glare. The proposed dashboard uses Mask R-CNN (Mask Region-based Convolutional Neural Network) for instance image segmentation to detect, localize and classify the on-road obstacles. In addition to the image segmentation, an object-distance measurement algorithm (ODMA) is developed to calculate the distance between on-road obstacles and the Ego Vehicle (EGV). The segmented on-road obstacles and their distances are plotted on the driver guidance window (DGW) of the dashboard. The proposed IDGDB is tested in VIT Vellore campus roads in both daylight and low-light conditions. The experimental results are satisfactory as they are very close to the ground truth values. By providing real-time information, IDGDB empowers drivers to make informed decisions, contributing significantly to the reduction of road accidents and fostering safer road environments during poor visibility conditions.
  • SteeringNET - A Deep-Learning based Obstacle Avoidance Approach for Autonomous Driving
    P Shunmuga Perumal, Husain Kanchwala, Yong Wang, V. Pandiyaraju, Nikil Krishnakumar, et al.
    2024 3rd International Conference on Artificial Intelligence for Internet of Things Aiiot 2024, 2024
    In this paper, a deep-learning based model named SteeringNET is proposed for obstacles avoidance. Three categories of obstacles were chosen, namely, two-wheelers, cars, and buses. The Ego Vehicle (EGV) was defined using a kinematic model and integrated with the Adaptive Model Predictive Control (MPC) to simulate the obstacle avoidance strategies for human drivers. The dataset for the human driver obstacle avoidance trajectories was generated using MATLAB simulations. A total of 14040 trajectories: 5400, 2160 and 6480 for stationary two-wheeler, car, bus obstacles were obtained. Conventional MPC based models are computationally expensive for obstacle-free trajectory generation and are unsuitable for real-time applications. Our model readily predicts the throttle, steering angle values for negotiating different obstacles and the prediction time is significantly lesser than the Adaptive MPC. Four different versions of this model are implemented namely, Fully Connected Neural Network (FCNN), FCNN with custom loss, Long Short-Term Memory (LSTM) and LSTM with custom loss. The experimental results show that LSTM with custom loss algorithm outperforms the other three deep-learning models.
  • LaneScanNET: A deep-learning approach for simultaneous detection of obstacle-lane states for autonomous driving systems
    P. Shunmuga Perumal, Yong Wang, M. Sujasree, Shobhit Tulshain, Saksham Bhutani, et al.
    Expert Systems with Applications, 2023
  • Coal fire détection and prévention system using IoT
    V. Pandiyaraju, P. Shunmuga Perumal, V. Muthumanikandan
    Cyber Physical System Solutions for Smart Cities, 2023
    Coal is one of the major natural sources of power production. It contributes to about 56% of the total production. Conventionally, coal is stored in stockpiles for production of electricity without any logs. Storage of coal for a longer time in the open type stockpile results in self-oxidation of coal, which leads to increased ignition temperature. Detection and prevention of spontaneous combustion and self-ignition stands to be major issues in stockpile. This chapter proposes an automated system using internet of things (IoT), which aids in detecting the fire at an earlier stage and to prevent it, thereby avoiding economic loss. Wireless sensor nodes are deployed to detect the parameters such as temperature, humidity, gases from the stockpile, and the data is transmitted to the server and to the ground station with the aid of GSM modules. Data is monitored in the ground station, and the critical values are evaluated to prevent fire by detecting it at its early stages. The system is implemented in an open rail coal stockpile, and the data is represented in the form of graph for evaluation.
  • Intelligent advice system for human drivers to prevent overtaking accidents in roads
    P. Shunmuga Perumal, Yong Wang, M. Sujasree, Venkat Mukthineni, Soorya Ram Shimgekar
    Expert Systems with Applications, 2022
  • A Comparative Assessment of Deep Neural Network Models for Detecting Obstacles in the Real Time Aerial Railway Track Images
    R. S. Rampriya, R. Suganya, Sabari Nathan, P. Shunmuga Perumal
    Applied Artificial Intelligence, 2022
    Obstacles on the railway track leading to derailment accidents that cause significant damages to the railway in terms of killed and injuries over the years. Count of accident is increasing day by day due to its causes such as boulders on track, trees falling on the gauge, etc. Monitoring these events has been possible with humans working in railways. But when it comes to the real-time scenario, it turns to fatal work and requires more workers, particularly in a dangerous area. Also, this manual monitoring is not adequate to halt derailment accidents. In this perspective, railroad obstacle detection from aerial images has been growing as a trending research topic under artificial intelligence. Also, this mandates the assessment of familiar and latest deep neural network models such as CenterNet Hourglass, EfficientDet, Faster RCNN, SSD Mobile Net, SSD ResNet, and YOLO that detects the violator of accidents with the aid of our own developed Rail Obstacle Detection Dataset (RODD). These detectors were implemented on real-time aerial railway track images captured by Unmanned Aerial Vehicle (UAV) in India. Initially, the input images in the collected datasets were undergone to data preprocessing after that; the above mentioned deep neural models were trained individually. After that, the experiment is analyzed based on training, time, and performance metrics. At last, the results are visualized, evaluated, and compared; hence based on the performance, some effective deep neural network models have identified for detecting obstacles. The result shows that SSD Mobile Net and Faster RCNN can be used for railroad obstacle detection even in the different lighting conditions in railway with the accuracy of 96.75% and 84.75%, respectively.
  • An insight into crash avoidance and overtaking advice systems for Autonomous Vehicles: A review, challenges and solutions
    P. Shunmuga Perumal, M. Sujasree, Suresh Chavhan, Deepak Gupta, Venkat Mukthineni, et al.
    Engineering Applications of Artificial Intelligence, 2021
  • UAV assisted automated remote monitoring and control system for smart water bodies
    P. Shunmuga Perumal, A. Samson Arun Raj, B. M. S. Bharathi, G. Mohan Raju, K. Yogeswari
    Proceedings 2017 2nd International Conference on Recent Trends and Challenges in Computational Models Icrtccm 2017, 2017
  • Smart terrace gardening with intelligent roof control algorithm for water conservation
    V. Pandiyaraju
    Pakistan Journal of Agricultural Sciences, 2017
  • WSN lifetime analysis: Intelligent UAV and Arc selection algorithm for energy conservation in isolated wireless sensor networks
    P. Perumal, V. R. Uthariaraj, V. R. E. Christo
    Ksii Transactions on Internet and Information Systems, 2015
  • Intelligent UAV-assisted localisation to conserve battery energy in military sensor networks
    P. Shunmuga Perumal, V. Rhymend Uthariaraj, V.R. Elgin Christo
    Defence Science Journal, 2014
  • Novel SP-CSSD based three dimensional localization for energy conservation in wireless sensor networks
    International Journal of Applied Engineering Research, 2014
  • Novel steam powered gravity assisted standalone power system (SP-GA-SP system) design for remote wireless sensor networks
    P. Shunmuga Perumal, V. Rhymend Uthariaraj, V.R. Elgin Christo
    Applied Mechanics and Materials, 2013
  • Novel localization of sensor nodes in wireless sensor networks using co-ordinate signal strength database
    P. Shunmuga Perumal, V. Rhymend Uthariaraj
    Procedia Engineering, 2012

RECENT SCHOLAR PUBLICATIONS

  • 5G-Enabled Interactive Sugarcane Protection Networks for Farmers and Experts: Custom Sugarcane Dataset Trained SPIDCNet for Under-Canopy Sugarcane Insect and Disease Detection
    PS Perumal, S Maheshkumar, R Viswanathan, C Raj, M SaqibDar, ...
    Smart Agricultural Technology, 102134 , 2026
    2026
  • Intelligent Driver Guidance Dashboard Framework to Prevent Road Accidents in Poor Visibility Conditions
    PS Perumal, VA Mamlesh, L Rahul, S Tiwari
    2024 International Conference on Computational Intelligence and Network … , 2024
    2024
    Citations: 1
  • Sugarcane Internode Dataset: SIDCNet for Detection and Counting of Sugarcane Internodes for Precision Agriculture
    S Maheshkumar, PS Perumal
    2024 International Conference on Computational Intelligence and Network … , 2024
    2024
    Citations: 1
  • Lightweight railroad semantic segmentation network and distance estimation for railroad Unmanned aerial vehicle images
    RS Rampriya, S Nathan, R Suganya, SB Prathiba, PS Perumal, W Wang
    Engineering Applications of Artificial Intelligence 134, 108620 , 2024
    2024
    Citations: 18
  • SteeringNET-A Deep-Learning based Obstacle Avoidance Approach for Autonomous Driving
    PS Perumal, H Kanchwala, Y Wang, V Pandiyaraju, N Krishnakumar, ...
    2024 3rd International Conference on Artificial Intelligence For Internet of … , 2024
    2024
    Citations: 2
  • LaneScanNET: A deep-learning approach for simultaneous detection of obstacle-lane states for autonomous driving systems
    PS Perumal, Y Wang, M Sujasree, S Tulshain, S Bhutani, MK Suriyah, ...
    Expert Systems with Applications 233, 120970 , 2023
    2023
    Citations: 40
  • Coal Fire Detection and Prevention System Using IoT
    V Pandiyaraju, PS Perumal, V Muthumanikandan
    Cyber-Physical System Solutions for Smart Cities, 36-51 , 2023
    2023
    Citations: 1
  • A comparative assessment of deep neural network models for detecting obstacles in the real time aerial railway track images
    RS Rampriya, R Suganya, S Nathan, PS Perumal
    Applied Artificial Intelligence 36 (1), 2018184 , 2022
    2022
    Citations: 36
  • Intelligent advice system for human drivers to prevent overtaking accidents in roads
    PS Perumal, Y Wang, M Sujasree, V Mukthineni, SR Shimgekar
    Expert Systems with Applications 199, 117178 , 2022
    2022
    Citations: 30
  • Wireless Sensor Network Assisted Intelligent Drip Irrigation System for Water Conservation in Agriculture
    V Pandiyaraju, PS PERUMAL, VE ARASI, A KANNAN
    2022
    Citations: 2
  • An insight into crash avoidance and overtaking advice systems for autonomous vehicles: A review, challenges and solutions
    PS Perumal, M Sujasree, S Chavhan, D Gupta, V Mukthineni, ...
    Engineering applications of artificial intelligence 104, 104406 , 2021
    2021
    Citations: 88
  • Lidar Based Intelligent Obstacle Avoidance System for Autonomous Ground Vehicles
    KG P. Shunmuga Perumal, M. Sujasree, K. Siddhardha
    International Journal of Recent Technology and Engineering, 8 (6), 2466- 247 , 2020
    2020
    Citations: 3
  • Smart terrace gardening with intelligent roof control algorithm for water conservation.
    V Pandiyaraju, PS Perumal, A Kannan, LS Ramesh
    2017
    Citations: 13
  • Uav assisted automated remote monitoring and control system for smart water bodies
    PS Perumal, ASA Raj, BMS Bharathi, GM Raju, K Yogeswari
    2017 Second International Conference on Recent Trends and Challenges in … , 2017
    2017
    Citations: 9
  • Dynamic Waypoint Navigation Assisted Agricultural Flying Vehicle for Field Data Collection
    V Pandiyaraju, PS Perumal, LS Ramesh, S Ganapathy, A Kannan
    Asian Journal of Research in Social Sciences and Humanities 6 (12), 448-457 , 2016
    2016
    Citations: 3
  • WSN Lifetime Analysis: Intelligent UAV and Arc Selection Algorithm for Energy Conservation in Isolated Wireless Sensor Networks.
    PS Perumal, VR Uthariaraj, VR Christo
    KSII Transactions on Internet & Information Systems 9 (3) , 2015
    2015
    Citations: 7
  • Intelligent UAV-assisted localisation to conserve battery energy in military sensor networks
    PS Perumal, VR Uthariaraj, VRE Christo
    Defence Science Journal 64 (6), 557-563 , 2014
    2014
    Citations: 15
  • Novel Steam Powered Gravity Assisted Standalone Power System (SP-GA-SP System) Design for Remote Wireless Sensor Networks
    PS Perumal, VR Uthariaraj, VRE Christo
    Applied Mechanics and Materials 440, 248-253 , 2014
    2014
    Citations: 1
  • Novel SP-CSSD based three dimensional localization for energy conservation in wireless sensor networks
    VREC P.Shunmuga Perumal, V.Rhymend Uthariaraj
    International Journal of Applied Engineering Research 9 (23), 21217-21230 , 2014
    2014
  • Gravitational Potential Energy Propelled Novel Power Generator
    VREC P.Shunmuga Perumal, V.Rhymend Uthariaraj
    The Patent Office Journal, INDIA, 8651 , 2013
    2013

MOST CITED SCHOLAR PUBLICATIONS

  • An insight into crash avoidance and overtaking advice systems for autonomous vehicles: A review, challenges and solutions
    PS Perumal, M Sujasree, S Chavhan, D Gupta, V Mukthineni, ...
    Engineering applications of artificial intelligence 104, 104406 , 2021
    2021
    Citations: 88
  • LaneScanNET: A deep-learning approach for simultaneous detection of obstacle-lane states for autonomous driving systems
    PS Perumal, Y Wang, M Sujasree, S Tulshain, S Bhutani, MK Suriyah, ...
    Expert Systems with Applications 233, 120970 , 2023
    2023
    Citations: 40
  • A comparative assessment of deep neural network models for detecting obstacles in the real time aerial railway track images
    RS Rampriya, R Suganya, S Nathan, PS Perumal
    Applied Artificial Intelligence 36 (1), 2018184 , 2022
    2022
    Citations: 36
  • Intelligent advice system for human drivers to prevent overtaking accidents in roads
    PS Perumal, Y Wang, M Sujasree, V Mukthineni, SR Shimgekar
    Expert Systems with Applications 199, 117178 , 2022
    2022
    Citations: 30
  • Lightweight railroad semantic segmentation network and distance estimation for railroad Unmanned aerial vehicle images
    RS Rampriya, S Nathan, R Suganya, SB Prathiba, PS Perumal, W Wang
    Engineering Applications of Artificial Intelligence 134, 108620 , 2024
    2024
    Citations: 18
  • Intelligent UAV-assisted localisation to conserve battery energy in military sensor networks
    PS Perumal, VR Uthariaraj, VRE Christo
    Defence Science Journal 64 (6), 557-563 , 2014
    2014
    Citations: 15
  • Smart terrace gardening with intelligent roof control algorithm for water conservation.
    V Pandiyaraju, PS Perumal, A Kannan, LS Ramesh
    2017
    Citations: 13
  • Uav assisted automated remote monitoring and control system for smart water bodies
    PS Perumal, ASA Raj, BMS Bharathi, GM Raju, K Yogeswari
    2017 Second International Conference on Recent Trends and Challenges in … , 2017
    2017
    Citations: 9
  • WSN Lifetime Analysis: Intelligent UAV and Arc Selection Algorithm for Energy Conservation in Isolated Wireless Sensor Networks.
    PS Perumal, VR Uthariaraj, VR Christo
    KSII Transactions on Internet & Information Systems 9 (3) , 2015
    2015
    Citations: 7
  • Novel localization of sensor nodes in wireless sensor networks using co-ordinate signal strength database
    PS Perumal, VR Uthariaraj
    Procedia Engineering 30, 662-668 , 2012
    2012
    Citations: 5
  • Lidar Based Intelligent Obstacle Avoidance System for Autonomous Ground Vehicles
    KG P. Shunmuga Perumal, M. Sujasree, K. Siddhardha
    International Journal of Recent Technology and Engineering, 8 (6), 2466- 247 , 2020
    2020
    Citations: 3
  • Dynamic Waypoint Navigation Assisted Agricultural Flying Vehicle for Field Data Collection
    V Pandiyaraju, PS Perumal, LS Ramesh, S Ganapathy, A Kannan
    Asian Journal of Research in Social Sciences and Humanities 6 (12), 448-457 , 2016
    2016
    Citations: 3
  • SteeringNET-A Deep-Learning based Obstacle Avoidance Approach for Autonomous Driving
    PS Perumal, H Kanchwala, Y Wang, V Pandiyaraju, N Krishnakumar, ...
    2024 3rd International Conference on Artificial Intelligence For Internet of … , 2024
    2024
    Citations: 2
  • Wireless Sensor Network Assisted Intelligent Drip Irrigation System for Water Conservation in Agriculture
    V Pandiyaraju, PS PERUMAL, VE ARASI, A KANNAN
    2022
    Citations: 2
  • Intelligent Driver Guidance Dashboard Framework to Prevent Road Accidents in Poor Visibility Conditions
    PS Perumal, VA Mamlesh, L Rahul, S Tiwari
    2024 International Conference on Computational Intelligence and Network … , 2024
    2024
    Citations: 1
  • Sugarcane Internode Dataset: SIDCNet for Detection and Counting of Sugarcane Internodes for Precision Agriculture
    S Maheshkumar, PS Perumal
    2024 International Conference on Computational Intelligence and Network … , 2024
    2024
    Citations: 1
  • Coal Fire Detection and Prevention System Using IoT
    V Pandiyaraju, PS Perumal, V Muthumanikandan
    Cyber-Physical System Solutions for Smart Cities, 36-51 , 2023
    2023
    Citations: 1
  • Novel Steam Powered Gravity Assisted Standalone Power System (SP-GA-SP System) Design for Remote Wireless Sensor Networks
    PS Perumal, VR Uthariaraj, VRE Christo
    Applied Mechanics and Materials 440, 248-253 , 2014
    2014
    Citations: 1
  • Removal of Radio Irregularity Crisis in WSN Localization using Enhanced Co-Ordinate Signal Strength Database
    PSPVR Uthariaraj
    IEEE, Devices, Circuits and Systems (ICDCS), 2012 International Conference … , 2012
    2012
    Citations: 1
  • 5G-Enabled Interactive Sugarcane Protection Networks for Farmers and Experts: Custom Sugarcane Dataset Trained SPIDCNet for Under-Canopy Sugarcane Insect and Disease Detection
    PS Perumal, S Maheshkumar, R Viswanathan, C Raj, M SaqibDar, ...
    Smart Agricultural Technology, 102134 , 2026
    2026