Search Results - "2022 18th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)"

A Spatio-temporal Deep Learning Approach for Underwater Acoustic Signals Classification by Alouani, Zakaria, Hmamouche, Youssef, Khamlichi, Btissam El, Seghrouchni, Amal El Fallah

“…Target recognition from underwater acoustic signals is a major challenge in surveillance systems, especially in military and defense fields. Deep learning…”
Get full text

Fusion Tree Network for RGBT Tracking by Cheng, Zhiyuan, Lu, Andong, Zhang, Zhang, Li, Chenglong, Wang, Liang

“…RGBT tracking is often affected by complex scenes (i.e., occlusions, scale changes, noisy background, etc). Existing works usually adopt a single-strategy RGBT…”
Get full text

MASK-MORPH: Does Morphing of Custom 3D Face Masks Threatens the Face Recognition Systems? by Ramachandra, Raghavendra, Marcel, Sebastien

“…Face Recognition Systems (FRS) are vulnerable to morphing attacks that are targeted towards highly secured applications, including Automatic Border Control…”
Get full text

An End to End Encoder-Decoder Network with Multi-scale Feature Pulling for Detecting Local Changes From Video Scene by Panda, Manoj Kumar, Subudhi, Badri Narayan, Bouwmans, Thierry, Jakheytiya, Vinit, Veerakumar, T.

“…Local change detection for moving object detection is an essential step in any computer vision task. The most well-known technique is background subtraction…”
Get full text

Real time Vehicle Color Recognition on a budget: an investigation on the usage of CNN architectures by Campisi, Simone, Colombini, Luca, Lovato, Alberto, Odone, Francesca, Noceti, Nicoletta

“…In this work, we consider the problem of vehicle color recognition and target scenarios with limited computational resources. Indeed, in real traffic…”
Get full text

Crowd counting Using DRL-based segmentation and RL-based density estimation by Elharrouss, Omar, Almaadeed, Noor, Al-Maadeed, Somaya, Abualsaud, Khalid, Mohamed, Amr, Khattab, Tamer

“…People counting is one of the computer vision tasks that can be useful for crowd management. In addition, estimating the crowdedness of a surveilled scene for…”
Get full text

Dual-valued Neural Networks by Kozlov, Dmitry, Pavlov, Stanislav, Zuev, Alexander, Bakulin, Mikhail, Krylova, Mariya, Kharchikov, Igor

“…The majority of existing neural networks operate with real-valued representation of data. However, there are multiple tasks in which the input is…”
Get full text

Utilizing Crowd Collectiveness to Enhance Bottleneck Detection Based on the Lagrangian Framework by Simon, Maik, Bochinski, Erik, Kuchhold, Markus, Sikora, Thomas

“…At large events and other crowded areas narrowed passages create a major safety risk for the involved people. We present a novel approach to automatically…”
Get full text

SAR Image Denoising in High Dynamic Range with Speckle and Thermal Noise Refinement Modeling by Han, Ji-Hoon, Nam, Woo-Jeoung, Lee, Seong-Whan

“…Synthetic Aperture Radar (SAR) images inevitably contain speckle noise. Despeckling SAR images are typically represented as linear forms due to the consistency…”
Get full text

Reliability Scoring for the Recognition of Degraded License Plates by Maier, Anatol, Moussa, Denise, Spruck, Andreas, Seiler, Jurgen, Riess, Christian

“…Criminal investigations oftentimes need the identification of license plates of escape vehicles. The vehicles may be recorded by low-quality cameras in the…”
Get full text

UPM-GTI-Face: A dataset for the evaluation of the impact of distance and masks in face detection and recognition systems by Rodrigo, Marcos, Gonzalez-Sosa, Ester, Cuevas, Carlos, Garcia, Narciso

“…We present a novel dataset for the evaluation of face detection and recognition algorithms in challenging surveillance scenarios. The dataset consists in 4K…”
Get full text

FRIDA: Fisheye Re-Identification Dataset with Annotations by Cokbas, Mertcan, Bolognino, John, Konrad, Janusz, Ishwar, Prakash

“…Person re-identification (PRID) from side-mounted rectilinear-lens cameras is a well-studied problem. On the other hand, PRID from overhead fisheye cameras is…”
Get full text

Vision Transformers for Road Accident Detection from Dashboard Cameras by Hajri, Feten, Fradi, Hajer

“…Road accidents are increasing at a worrying rate and have raised one of the major concerns in traffic road monitoring. Their detection is becoming a very…”
Get full text

Hand-Object Interaction Reasoning by Ma, Jian, Damen, Dima

“…This paper proposes an interaction reasoning network for modelling spatio-temporal relationships between hands and objects in egocentric video. The proposed…”
Get full text

Graph Structure Learning Boosted Neural Network for Image Segmentation by Liu, Jinde, Zhang, Zhang

“…Although Convolutional Neural Networks have made significant progress in image segmentation, it remains inadequate for exploring the structural relationships…”
Get full text

RCRL: Replay-based Continual Representation Learning in Multi-task Super-Resolution by Park, Jinyong, Kim, Minha, Woo, Simon S.

“…Super-resolution (SR) aims to recover high-resolution (HR) images from low-resolution (LR) images. Recently, various attempts, e.g., unsupervised SR models and…”
Get full text

Background Subtraction Network Module Ensemble for Background Scene Adaptation by Hamada, Taiki, Minematsu, Tsubasa, Simada, Atsushi, Okubo, Fumiya, Taniguchi, Yuta

“…Background subtraction networks outperform traditional hand-craft background subtraction methods. The main advantage of background subtraction networks is…”
Get full text

Customer Behavior Recognition Adaptable for Changing Targets in Retail Environments by Wen, Jiahao, Abe, Toru, Suganuma, Takuo

“…Recognizing Customer Behavior (CB) from videos of instore cameras is important to smart retail solutions. Because of possible changes in retail needs and…”
Get full text

Fast High-Resolution Fingerprint Recognition using Domain-Knowledge Infused Global Descriptors by Nema, Aneesh, Anand, Vijay, Kanhangad, Vivek

“…High-resolution fingerprint recognition is mainly centred around local descriptors created using pore patches. Although these methods provide good verification…”
Get full text

FPDM: Fisheye Panoptic segmentation dataset for Door Monitoring by Thioune, Mohamed, Chafik, Sanaa, Mahtani, Ankur, Laurendin, Olivier, Boudra, Safia

“…Most existing panoptic segmentation datasets are not suited for applications in the railway environment. This paper introduces a new dataset composed of video…”
Get full text