مجال التميز | تميز دراسي وبحثي |
البحوث المنشورة |
|
البحث (1): | |
عنوان البحث: |
Improving Object Detection Performance Using Scene Contextual Constraints |
رابط إلى البحث: | |
تاريخ النشر: |
09/07/2020 |
موجز عن البحث: |
Contextual information, such as the co-occurrence of objects and the spatial and relative size among objects, provides rich and complex information about digital scenes. It also plays an important role in improving object detection and determining out-of-context objects. In this work, we present contextual models that leverage contextual information (16 contextual relationships are applied in this paper) to enhance the performance of two of the state-of-the-art object detectors (i.e., Faster RCNN and YOLO), which are applied as a post-processing process for most of the existing detectors, especially for refining the confidences and associated categorical labels, without refining bounding boxes. We experimentally demonstrate that our models lead to enhancement in detection performance using the most common dataset used in this field (MSCOCO), where in some experiments PASCAL2012 is also used.We also show that iterating the process of applying our contextual models also enhances the detection performance further. |
المؤتمرات العلمية |
|
المؤتمر (1): | |
عنوان المؤتمر: |
25th International Conference on Pattern Recognition (ICPR’2020) |
تاريخ الإنعقاد: |
15/01/2020 |
مكان الإنعقاد: |
Milan (virtual) |
طبيعة المشاركة: |
Poster presentation |
عنوان المشاركة: |
Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detection |
ملخص المشاركة: |
Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low amplitude perturbations, barely perceptible by the human eye, can lead to a drastic reduction in labelling performance. This article proposes a new context module, called Transformer Encoder Detector Module that can be applied to an object detector to (i) improve the labelling of object instances; and (ii) improve the detector’s robustness to adversarial attacks. The proposed model achieves higher mAP, F1 scores and AUC average score of up to 13% compared to the baseline Faster-RCNN detector, and an mAP score 8 points higher on images subjected to FFF or UAP attacks due to the inclusion of both contextual and visual features extracted from scene and encoded into the model. The result demonstrates that a simple ad-hoc context module can improve the reliability of object detectors significantly. |
الرابط: | |
المؤتمر (2): | |
عنوان المؤتمر: |
IEEE ICDL-Epirob’2019 conference |
تاريخ الإنعقاد: |
22/08/2019 |
مكان الإنعقاد: |
Oslo, Norway |
طبيعة المشاركة: |
Paper presentation |
عنوان المشاركة: |
Contextual Relabelling of Detected Objects |
ملخص المشاركة: |
Contextual information, such as the co-occurrence of objects and the spatial and relative size among objects provides deep and complex information about scenes. It also can play an important role in improving object detection. In this work, we present two contextual models (rescoring and re-labeling models) that leverage contextual information (16 contextual relationships are applied in this paper) to enhance the state of-the-art RCNN-based object detection (Faster RCNN). We experimentally demonstrate that our models lead to enhancement in detection performance using the most common dataset used in this field (MSCOCO). |
الرابط: | |
المؤتمر (3): | |
عنوان المؤتمر: |
CIARP 2017: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications |
تاريخ الإنعقاد: |
10/11/2017 |
مكان الإنعقاد: |
Valparaiso, Chile |
طبيعة المشاركة: |
Paper presentation |
عنوان المشاركة: |
Edge Detection Based on Digital Shape Elongation Measure |
ملخص المشاركة: |
In this paper, we justify the hypothesis that the methods based on the tools designed to cope with digital images can outperform the standard techniques, usually coming from differential calculus and differential geometry. Herein, we have employed the shape elongation measure, a well-known shape based image analysis tool, to offer a solution to the edge detection problem. The shape elongation measure, as used in this paper, is a numerical characteristic of discrete shape, computable for all discrete point sets, including digital images. Such a measure does not involve any of the infinitesimal processes for its computation. The method proposed can be applied to any digital image directly, without the need of any pre-processing. |
الرابط: |
https://link.springer.com/chapter/10.1007/978-3-319-75193-1_3 |
فيصل عبدالرحمن ظافر العمري
دكتوراه
العلوم والتقنية
University of Exeter