Multi-class Concealed Object detection system using Yolov9 Integrated with CBAM / (Record no. 614891)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 02923nam a22001577a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 629.8 |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Chaghtai, Mubeen Naeem |
| 245 ## - TITLE STATEMENT | |
| Title | Multi-class Concealed Object detection system using Yolov9 Integrated with CBAM / |
| Statement of responsibility, etc. | Mubeen Naeem Chaghtai |
| 264 ## - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE | |
| Place of production, publication, distribution, manufacture | Islamabad : |
| Name of producer, publisher, distributor, manufacturer | SMME- NUST; |
| Date of production, publication, distribution, manufacture, or copyright notice | 2025. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 95p. |
| Other physical details | Soft Copy |
| Dimensions | 30cm |
| 500 ## - GENERAL NOTE | |
| General note | Smart city development places high emphasis on high-performance safety solutions to<br/>counter city security threats such as street crime and increased numbers of unconcealed<br/>and concealed objects. Although unconcealed objects are visible threats that are relatively<br/>easy to identify, their multi-class counterparts that are concealed pose high challenges<br/>given that they are not visible, especially within dense thermal grayscale scenes. Prevalent<br/>detection solutions like metal detectors and infrared cameras usually fail to correctly<br/>recognize multi-class objects, either unconcealed or concealed objects, which often result<br/>in false negatives and require human verification. This research presents an enhanced<br/>multiclass object detection model using YOLOv9 combined with Convolutional Block<br/>Attention Modules (CBAM) to improve improvement of inference time with a special<br/>emphasis on detecting concealed objects. The model embeds channel and spatial attention<br/>from CBAM within YOLOv9’s backbone and head to enhance feature representation for<br/>multi-scale object detection and efficiently handle unconcealed as well as concealed<br/>objects from thermal images. The model applies YOLOv9’s Programmable Gradient<br/>Information (PGI) and Generalized Efficient Layer Aggregation Network (GELAN) to<br/>streamline feature extraction and reduce loss of information with enhanced multi-target<br/>detection accuracy. The model was trained and tested on a set of 8,600 grayscale image<br/>augmentations, spanning four object classes (revolvers, tasers, knives, and guns), with<br/>strict preprocessing to keep classes balanced and semantically sound. The YOLOv9-<br/>CBAM structure obtains a mean Average Precision (mAP@0.5) of 0.954 and mAP@0.5-<br/>0.95 of 0.948 compared to the baseline YOLOv9's mAP@0.5 of 0.944 and mAP@0.5-0.95<br/>of 0.940, representing accuracy improvements. The CBAM-augmented model achieves<br/>1.9% faster inference speed than the baseline, achieving optimal performance with both<br/>unconcealed and hidden object detection at optimized computation efficiency. The efficient<br/>and highly effective system best suits real-time smart city security applications like airport<br/>screening, patrol by police, and critical infrastructure security, reducing queuing time<br/>considerably while significantly enhancing automated threat detection efficiency. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | MS Robotics and Intelligent Machine Engineering |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervisor : Dr Shahbaz Khan |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="http://10.250.8.41:8080/xmlui/handle/123456789/55012">http://10.250.8.41:8080/xmlui/handle/123456789/55012</a> |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | |
| Koha item type | Thesis |
| Withdrawn status | Permanent Location | Current Location | Shelving location | Date acquired | Full call number | Barcode | Koha item type |
|---|---|---|---|---|---|---|---|
| School of Mechanical & Manufacturing Engineering (SMME) | School of Mechanical & Manufacturing Engineering (SMME) | E-Books | 09/26/2025 | 629.8 | SMME-TH-1172 | Thesis |