Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : JOIV : International Journal on Informatics Visualization

Exploration of The Impact of Kernel Size for YOLOv5-based Object Detection on Quadcopter Rissa Rahmania; Felix Corputty; Suryo Adhi Wibowo; Dany Eka Saputra; Annisa Istiqomah
JOIV : International Journal on Informatics Visualization Vol 6, No 3 (2022)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.6.3.898

Abstract

Drones or quadcopters have been widely used in various fields based on deep learning, especially object detection. However, drone vision characteristics such as occlusion and small objects are still being explored for performance in terms of accuracy and speed detection. The YOLO architecture is very commonly used for cases requiring high-speed detection. To overcome the limitations of drone vision, in this paper, we explore the size of the YOLOv5s backbone kernel in the shallowest convolutional layer to achieve better performance. The kernel is a filter that has a main role in the feature map, and it defines the size of the convolution matrix, and the resulting features in the shallowest convolutional layer are more representative of the case of object detection and recognition. The techniques can be divided into three major categories: (1) data preprocessing, which involves augmentation and normalization of the data, (2) kernel size exploration in the shallowest convolutional layer of the YOLOv5s, and (3) model implementation in the real environment using the quadcopter. The dataset consisted of four classes representing dragon fruit, snake fruit, banana, and pineapple, with a total of 8000 data. Exploration results with kernel size give promising results. Kernel sizes 5 and 7 give an mAP of 0.988. Through these results, modification of the kernel size provides an opportunity for more in-depth investigations, such as with the epoch parameter, padding scheme, and other optimization techniques.
Multi-Head Voting based on Kernel Filtering for Fine-grained Visual Classification Khairunnisa, Mutiarahmi; Wibowo, Suryo Adhi
JOIV : International Journal on Informatics Visualization Vol 9, No 2 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.2.2920

Abstract

Research on Fine-Grained Visual Classification (FGVC) faces a significant challenge in distinguishing objects with subtle differences within intra-class variations and inter-class similarities, which are critical for accurate classification. To address this complexity, many advanced methods have been proposed using feature coding, part-based components for modification, and attention-based efforts to facilitate different classification phases. Vision Transformers (ViT) has recently emerged as a promising competitor compared to other complex methods in FGVC applications for image recognition, which are mainly capable of capturing more fine-grained details and subtle inter-class differences with higher accuracy. While these advances have shown improvements in various tasks, existing methods still suffer from inconsistent learning performance across heads and layers in the multi-head self-attention (MHSA) mechanisms that result in suboptimal classification task performance. To enhance the performance of ViT, we propose an innovative approach that modifies the convolutional kernel.  Our method considerably improves the method's capacity to identify and highlight specific crucial characteristics required for classification by using an array of kernels. Experimental results show kernel sharpening outperforms other state-of-the-art approaches in improving accuracy across numerous datasets, including Oxford-IIIT Pet, CUB-200-2011, and Stanford Dogs. Our findings show that the suggested approach improves the method's overall performance in classification tasks by achieving more concentration and precision in recognizing discriminative areas inside pictures. Using kernel adjustments to improve Vision Transformers' ability to differentiate somewhat complicated visual features, our strategy offers a strong response to the problem of fine-grained categorization.
Co-Authors Achmad Rizal Adam Wisnu Pradana Agnes Gabriela Putri Winata Agus Pratondo Al Rasyid, Sadam Aldo Tripolyta Aldra Kasyfil Aziz Amara, Dhiva Byantika Angga Rusdinar ANGGUNMEKA LUHUR PRASASTI Anky Aditya P Annisa Istiqomah Asep Insani Atina Nur Azizah Aulia Aushaf Abidah Aulia, Agniya Tazkiya Aziz, Burhanuddin Bambang Hidayat Bambang Hidayat Bambang Setia Nugroho Budiyanto, Anggara Casi Setianingsih Dany Eka Saputra David Chandra Dawwam, Muhammad Devita Rahma Apriliani Dien Rahmawati Dini Himmah Al Aliyyah Al Aliyyah Djoko Heru Pamungkas Djoko Heru Pamungkas Dwiki Kurniawan Dyah Avita Sari Fahmi Oscandar Fahmi Oscandar Fajri, Farhan Ulil Farah Hana Kusumaputri Fathiyya, Dhiya Felix Corputty Fiky Y. Suratman Firdaus, Rifqi Fadhilah Fityanul Akhyar Gelar Budiman Gusdi, Angelita Hanaluthfina Nurhadiati Hashfi Fadhillah Hesty Susanti Hoka Cristian Son Hudzaifa, Muhammad Altaharik Huljannah, Miftah Humayra, Tia Hasna Husneni Mukhtar Indra Aulia Iwan Iwut Tritoasmoro Jangkung Raharjo Julyano , Muhammad Billy Khairunnisa, Mutiarahmi Koredianto Usman Kris Sujatmoko Kurnia Ramadani Kusnahadi Susanto Kusuma Nindia Rizki Lazuardi, Aldira Fadillah Ledya Novamizanti Liyana Faiza Lulud Annisa Ainun Mahmuddah Lyra Vega Ugi M. Faiz Nashrullah Maharani , Kartika Dwi Maharani, Kartika Dwi Mahfuz, Muhammad Rafi Maulana , Muhammad Dafa Mertu, Aidi Miftadi Sudjai Muhammad Alief Hidayah Baso Muhammad Azwar Zulmi Muhammad Raia Pratama Putra Wibowo Muthia Saada Nadya Sindi Safitri Nasirudin, Akhmad Yusuf Nauw, Alvaro Septra Dominggo Oriza Intani Prasaja Wibawa Utama Prihananto, Jeremia Pandu Putra Putri Utami Hafgianti Qomariyati, Laily Nur Rabby Fitriana Adawiyah Radhibilla, Maulaya Raditiana Patmasari Rahmalisty , Fiona Okki Rahmalisty, Fiona Okki Raihan Putra Darmawan Ramadhan, Ferdian Ilham Rambi, Wesli Yeremi Valentino Ricky Hilmi Sudrajad Rissa Rahmania Rissa Rahmania Rissa Rahmania Rissa Rahmania Rissa Rahmania, Rissa Rita Purnamasari Rizal , Syamsul Rofifi, M. Faiq Rosadi, Choiron Ruslan , Ramah Rinaldi Setiawan, Jonathan Vito Siddiq Wahyu Hidayat Sunaryo, Yacobus Susi Diriyanti Novalina Syahanifa , Nancy Olivia Syahanifa, Nancy Olivia Syamsul Rizal Syifa, Vito Devara Taufan Umbara Tembang Florian Falah Teuku Zulkarnain Muttaqien Unang Sunarya Viky Premeita Mitayani Vivian Alfionita Sutama Wahmisari Priharti Wahyu Maulana, Andi Wardani , Shania Widianto, Kiki Willy Anugrah Cahyadi Wiwit Ratri Wulandari Yacobus Sunaryo Yurika Ambar Lita Yuti Malinda