Bhowmik, Neelanjan
1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results
Kiefer, Benjamin, Kristan, Matej, Perš, Janez, Žust, Lojze, Poiesi, Fabio, Andrade, Fabio Augusto de Alcantara, Bernardino, Alexandre, Dawkins, Matthew, Raitoharju, Jenni, Quan, Yitong, Atmaca, Adem, Höfer, Timon, Zhang, Qiming, Xu, Yufei, Zhang, Jing, Tao, Dacheng, Sommer, Lars, Spraul, Raphael, Zhao, Hangyue, Zhang, Hongpu, Zhao, Yanyun, Augustin, Jan Lukas, Jeon, Eui-ik, Lee, Impyeong, Zedda, Luca, Loddo, Andrea, Di Ruberto, Cecilia, Verma, Sagar, Gupta, Siddharth, Muralidhara, Shishir, Hegde, Niharika, Xing, Daitao, Evangeliou, Nikolaos, Tzes, Anthony, Bartl, Vojtěch, Špaňhel, Jakub, Herout, Adam, Bhowmik, Neelanjan, Breckon, Toby P., Kundargi, Shivanand, Anvekar, Tejas, Desai, Chaitra, Tabib, Ramesh Ashok, Mudengudi, Uma, Vats, Arpita, Song, Yang, Liu, Delong, Li, Yonglin, Li, Shuman, Tan, Chenhao, Lan, Long, Somers, Vladimir, De Vleeschouwer, Christophe, Alahi, Alexandre, Huang, Hsiang-Wei, Yang, Cheng-Yen, Hwang, Jenq-Neng, Kim, Pyong-Kun, Kim, Kwangju, Lee, Kyoungoh, Jiang, Shuai, Li, Haiwen, Ziqiang, Zheng, Vu, Tuan-Anh, Nguyen-Truong, Hai, Yeung, Sai-Kit, Jia, Zhuang, Yang, Sophia, Hsu, Chih-Chung, Hou, Xiu-Yu, Jhang, Yu-An, Yang, Simon, Yang, Mau-Tsuen
The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection. The subchallenges were based on the SeaDronesSee and MODS benchmarks. This report summarizes the main findings of the individual subchallenges and introduces a new benchmark, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage. We provide statistical and qualitative analyses, and assess trends in the best-performing methodologies of over 130 submissions. The methods are summarized in the appendix. The datasets, evaluation code and the leaderboard are publicly available at https://seadronessee.cs.uni-tuebingen.de/macvi.
Operationalizing Convolutional Neural Network Architectures for Prohibited Object Detection in X-Ray Imagery
Webb, Thomas W., Bhowmik, Neelanjan, Gaus, Yona Falinie A., Breckon, Toby P.
The recent advancement in deep Convolutional Neural Network (CNN) has brought insight into the automation of X-ray security screening for aviation security and beyond. Here, we explore the viability of two recent end-to-end object detection CNN architectures, Cascade R-CNN and FreeAnchor, for prohibited item detection by balancing processing time and the impact of image data compression from an operational viewpoint. Overall, we achieve maximal detection performance using a FreeAnchor architecture with a ResNet50 backbone, obtaining mean Average Precision (mAP) of 87.7 and 85.8 for using the OPIXray and SIXray benchmark datasets, showing superior performance over prior work on both. With fewer parameters and less training time, FreeAnchor achieves the highest detection inference speed of ~13 fps (3.9 ms per image). Furthermore, we evaluate the impact of lossy image compression upon detector performance. The CNN models display substantial resilience to the lossy compression, resulting in only a 1.1% decrease in mAP at the JPEG compression level of 50. Additionally, a thorough evaluation of data augmentation techniques is provided, including adaptions of MixUp and CutMix strategy as well as other standard transformations, further improving the detection accuracy.