Hazry Desa
Thumbnail Image
Preferred name
Hazry Desa
Official Name
Desa, Hazry
Alternative Name
Desa, H.
Hazry, Desa
Desa, Hazy
Hazry, D.
Main Affiliation
Scopus Author ID
16642497100

Research Output

Filters

6
6
Reset filters

Settings
Now showing 1 - 6 of 6
  • Publication
    Aerial image semantic segmentation based on 3D fits a small dataset of 1D
    ( 2023-12-01)
    Ahmed S.A.
    ;
    Hazry Desa
    ;
    Hussain A.S.T.
    Time restrictions and lack of precision demand that the initial technique be abandoned. Even though the remaining datasets had fewer identified classes than initially planned for the study, the labels were more accurate. Because of the need for additional data, a single network cannot categorize all the essential elements in a picture, including bodies of water, roads, trees, buildings, and crops. However, the final network gains some invariance in detecting these classes with environmental changes due to the different geographic positions of roads and buildings discovered in the final datasets, which could be valuable in future navigation research. At the moment, binary classifications of a single class are the only datasets that can be used for the semantic segmentation of aerial images. Even though some pictures have more than one classification, images of roads and buildings were only found in a significant number of samples. Then, the building datasets were pooled to produce a larger dataset and for the constructed models to gain some invariance on image location. Because of the massive disparity in sample size, road datasets needed to be integrated.
  • Publication
    Classification of semantic segmentation using fully convolutional networks based unmanned aerial vehicle application
    ( 2023-06-01)
    Ahmed S.A.
    ;
    Hazry Desa
    ;
    Hussain A.S.T.
    The classification of semantic segmentation-based unmanned aerial vehicle (UAV) application based on the datasets used in this work and the necessary data preprocessing steps for the optimization and implementation of the models are also involved. The optimization of the various models was done using the evaluation metrics and loss functions because deep neural networks (DNNs) are just about writing a cost function and its subsequent optimization. convolutional neural network (CNN) is a common type of artificial neural network (ANN) that has found application in numerous tasks, such as image and video recognition, image classification, recommender systems, financial time series, medical image analysis, and natural language processing. CNN is developed to automatically and adaptively learn spatial feature hierarchies via backpropagation using numerous building blocks, such as pooling, convolution, and fully connected layers. The result of identification was excellent. The image segmentation was detected and comprehend the actual components of an image down to the pixel level. The result created an entire image segmentation masks with instances using the new label editor in the label box.
  • Publication
    Object Detection and Instance Segmentation with YOLOV8: Progress and Limitations
    ( 2024-01-01)
    Lee L.J.
    ;
    Hazry Desa
    ;
    Muhammad Azizi Azizan
    ;
    Hussain A.S.T.
    ;
    Tanveer M.H.
    This research employs object detection and instance segmentation algorithms to distinguish between objects and backgrounds and to interpret the detected objects. The YOLOV8 (You Only Look Once) framework and COCO dataset are utilized for detecting and interpreting the objects. Additionally, the accuracy of detection, segmentation, and interpretation is tested by placing objects at various distances from the camera. The algorithm's performance was evaluated, and the results were documented. In the experiments, a sample of 11 objects was tested, and 8 of them were successfully detected at distances of 45cm, 75cm, 105cm, and 135cm. For instance, segmentation, segmentation maps appeared clean when detecting a single object but faced challenges when multiple objects overlapped.
  • Publication
    Implementation of deep neural networks learning on unmanned aerial vehicle based remote-sensing
    ( 2024-03-01)
    Ahmed S.A.
    ;
    Hazry Desa
    ;
    Hussain A.S.T.
    ;
    Taha T.A.
    Due to efficient and adaptable data collecting, unmanned aerial vehicle (UAV) has been a popular topic in computer vision (CV) and remote sensing (RS) in recent years. Inspiring by the recent success of deep learning (DL), several enhanced object identification and tracking methods have been broadly applied to a variety of UAV-related applications, including environmental monitoring, precision agriculture, and traffic management. In this research, we present efficient neural network (ENet), a unique deep neural network architecture designed exclusively for jobs demanding low latency operation. ENet is up to quicker, takes fewer floating-point operations per second (FLOPs), has fewer parameters, and offers accuracy comparable to or superior to that of previous models. We have tested it on the street and cityscapes reports on comparisons with current state-of-the-art approaches and the tradeoffs between a network's processing speed and accuracy. We give measurements of the proposed architecture's performance on embedded devices and offer software enhancements that might make ENet even quicker.
  • Publication
    Spraying Dispersion Analysis with Different Nozzle Types Using a UAV Spraying System in a Paddy Field
    ( 2023-01-01)
    Hazry Desa
    ;
    Muhammad Azizi Azizan
    ;
    Nik Noriman Zulkepli
    ;
    Nurfadzillah Ishak
    ;
    Tian T.Y.
    ;
    Yahya S.S.
    ;
    Shahrazel A.A.M.
    ;
    Mansor F.M.
    ;
    Aziz S.Z.A.
    ;
    Hussain A.S.T.
    This study investigates the ability of Unmanned Aerial Vehicle (UAV) spraying systems to be used as an agriculture spraying method in Malaysia. The operating height of the UAV was 1.5 m with three different nozzles were investigated within a wind speed of 1.15 m/s to determine spray uniformity and dispersion in the paddy field conditions. The results from these samples were evaluated by using ImageJ software. The results show that the droplet distribution by using an electrostatic centrifugal nozzle has a high average droplet density, which is 134.03 deposits/cm2 for the top area and 153.93 deposits/cm2 for the bottom area. The electrostatic centrifugal nozzle also testified to the high value of total droplet deposit at 3478 for the top area and 3255 for the bottom area.
      1
  • Publication
    Effect of Spraying Dispersion Using UAV Spraying System with Different Height at Paddy Field
    ( 2023-01-01)
    Hazry Desa
    ;
    Muhammad Azizi Azizan
    ;
    Nik Noriman Zulkepli
    ;
    Nurfadzillah Ishak
    ;
    Hang T.X.
    ;
    Yahya S.S.
    ;
    Shahrazel A.A.M.
    ;
    Mansor F.M.
    ;
    Aziz S.Z.A.
    ;
    Hussain A.S.T.
    This study investigated the UAV spraying system height in relation to spraying uniformity and dispersion. The operating heights of the UAV spraying system at heights of 1 m, 1.5 m, and 2 m from the hollow cone nozzles were investigated within a wind speed of 2.8 m/s. The tests were to determine the spray uniformity and dispersion on the water sensitive paper that was placed on the paddy plant. The results of water droplet samples were evaluated using ImageJ software. The results show the droplet distribution at 1.5 m height has high values for average droplet density, which is 162.7 deposits/cm²at the top area and 161.8 deposits/cm²at the bottom area. The percentage of coverage was also high, at 55.21% at the top area and 51.4% at the bottom area.
      1