Video surveillance using deep transfer learning and deep domain adaptation: Towards better generalization

Himeur, Yassine; Al‐Maadeed, Somaya; Kheddar, Hamza; Almaadeed, Noor; Abualsaud, Khalid; Mohamed, Amr; Khattab, Tamer

doi:10.1016/j.engappai.2022.105698

Cited by 37 publications

(8 citation statements)

References 340 publications

(213 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further subtasks are performed from these approaches such as re-identification [8] , tracking, and similarity matching [4,6,7]. Transfer learning has been widely utilized for its computing efficiency using existing pretrained models for video surveillance [2].…”

Section: Introductionmentioning

confidence: 99%

Vehicle Instance Segmentation Polygonal Dataset for Private Surveillance System

Ottakath¹,

Al-Maadeed²

2023

Preprint

View full text Add to dashboard Cite

Vehicle identification is an important task in traffic monitoring because it allows for efficient inference and provides a cause for action. Vehicle classification via deep learning and other approaches such as segmentation is a critical tool for re-identification. In this paper, instance segmentation is used to identify vehicle makes with license plate detection, allowing for better unique vehicle recognition for re-identification. A dataset is annotated and modified, for example, by segmenting it with polygonal bounding boxes that capture the vehicle's unique frontal features. In addition, license plate localization is performed. The results showed improved classification as well as a high mAP for the dataset when compared to previous approaches based on CNN and deformed CNN. Furthermore, a deep residual network and fully connected layer-based classification were utilized as the backbone for feature representation. Instance segmentation detects objects by segmenting and classifying regions of interest. The imbalance in the dataset is resolved using a mosaic-tiled approach, which produces greater precision than other approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

Vehicle Instance Segmentation Polygonal Dataset for Private Surveillance System

Ottakath¹,

Al-Maadeed²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Further subtasks are performed from these approaches such as re-identification [8] , tracking, and similarity matching [4,6,7]. Transfer learning has been widely utilized for its computing effeciency using existing pretrained models for video surveillance [2].…”

Section: Introductionmentioning

confidence: 99%

Polygonal Dataset for Vehicle Instance Segmentation for Private Surveillance System

Ottakath¹,

Al-Maadeed²

2023

Preprint

View full text Add to dashboard Cite

Vehicle identification is an important task in traffic monitoring because it allows for efficient inference and provides a cause for action. Vehicle classification via deep learning and other approaches such as segmentation is a critical tool for re-identification. In this paper, instance segmentation is used for vehicle make identification with license plate detection, allowing for better unique vehicle recognition for re-identification. An existing dataset is re-annotated and modified for polygonal segmentation of the vehicle’s unique frontal features, resulting in representation of the vehicle with its frontal form learned. In addition, an additional license plate identification class is added for efficient re-identification further down the re-identification and tracking pipeline. Furthermore, an additional class of license plate identification is added for efficient re-identification further down the re-identification and tracking pipeline. The results showed improved classification as well as a high mAP for the dataset when compared to previous approaches based on CNN and deformed CNN. Furthermore, a deep residual network and fully connected layer-based classification were utilized as the backbone for feature representation. Instance segmentation detects objects by segmenting and classifying regions of interest. The imbalance in the dataset is resolved using a mosaic-tiled approach, which produces greater precision than other approaches evaluated for in the paper.

show abstract

“…Further subtasks are performed from these approaches, such as re-identification [ 7 ], tracking, and similarity matching [ 8 , 9 , 10 ]. Transfer learning has been widely utilized for its computing efficiency using existing pre-trained models for video surveillance [ 11 ]. The requirement for robust vehicle identification lies in the need for public safety and security.…”

Section: Introductionmentioning

confidence: 99%

Vehicle Instance Segmentation Polygonal Dataset for a Private Surveillance System

Ottakath

Al-Maadeed

2023

Sensors

Self Cite

View full text Add to dashboard Cite

Vehicle identification and re-identification is an essential tool for traffic surveillance. However, with cameras at every corner of the street, there is a requirement for private surveillance. Automated surveillance can be achieved through computer vision tasks such as segmentation of the vehicle, classification of the make and model of the vehicle and license plate detection. To achieve a unique representation of every vehicle on the road with just the region of interest extracted, instance segmentation is applied. With the frontal part of the vehicle segmented for privacy, the vehicle make is identified along with the license plate. To achieve this, a dataset is annotated with a polygonal bounding box of its frontal region and license plate localization. State-of-the-art methods, maskRCNN, is utilized to identify the best performing model. Further, data augmentation using multiple techniques is evaluated for better generalization of the dataset. The results showed improved classification as well as a high mAP for the dataset when compared to previous approaches on the same dataset. A classification accuracy of 99.2% was obtained and segmentation was achieved with a high mAP of 99.67%. Data augmentation approaches were employed to balance and generalize the dataset of which the mosaic-tiled approach produced higher accuracy.

show abstract

Video surveillance using deep transfer learning and deep domain adaptation: Towards better generalization

Cited by 37 publications

References 340 publications

Vehicle Instance Segmentation Polygonal Dataset for Private Surveillance System

Vehicle Instance Segmentation Polygonal Dataset for Private Surveillance System

Polygonal Dataset for Vehicle Instance Segmentation for Private Surveillance System

Vehicle Instance Segmentation Polygonal Dataset for a Private Surveillance System

Contact Info

Product

Resources

About