“…DenseNet-169 training is accomplished using full body images for gender classification. AVSS 2018 challenge II [5], RAP [17], PETA [18], and DukeMTMC-reID [21] datasets are used to collect 1,45,386 full body images. Each image is resized to 350 × 140 resolution to preserve the spatial ratio of full body.…”
Section: Densenet-169 Training For Gender Classificationmentioning
confidence: 99%
“…The proposed algorithm achieves highest average IoU for 20 sequences {TS. 2,3,5,7,8,9,13,14,16,17,20,22,24,26,27,34,36,37, 38, 39} out of 41. The above sequences cover all the difficulty levels in the dataset.…”
Section: Performance Analysismentioning
confidence: 99%
“…Pose annotations in the dataset are avoided by PGDM which transfer the existing pose estimation model knowledge to pedestrian attribute database. The evaluation uses RAP [17], PETA [18] and PA-100K [19] large scale pedestrian attribute datasets. Given the input image, Part-based Convolutional Baseline (PCB) [13] 1501 [20] dataset.…”
Section: Introductionmentioning
confidence: 99%
“…Researchers are extensively using PETA [18], Market-1501 [20], DukeMTMC-reID [21], CUHK03 [22] and RAP [17] large scale pedestrian datasets for person identification or re-identification. These datasets consist of a gallery of cropped images of persons and annotated soft biometric attributes.…”
Visual appearance-based person retrieval is a challenging problem in surveillance. It uses attributes like height, cloth color, cloth type and gender to describe a human. Such attributes are known as soft biometrics. This paper proposes person retrieval from surveillance video using height, torso cloth type, torso cloth color and gender. The approach introduces an adaptive torso patch extraction and bounding box regression to improve the retrieval. The algorithm uses fine-tuned Mask R-CNN and DenseNet-169 for person detection and attribute classification respectively. The performance is analyzed on AVSS 2018 challenge II dataset and it achieves 11.35% improvement over state-of-the-art based on average Intersection over Union measure.
“…DenseNet-169 training is accomplished using full body images for gender classification. AVSS 2018 challenge II [5], RAP [17], PETA [18], and DukeMTMC-reID [21] datasets are used to collect 1,45,386 full body images. Each image is resized to 350 × 140 resolution to preserve the spatial ratio of full body.…”
Section: Densenet-169 Training For Gender Classificationmentioning
confidence: 99%
“…The proposed algorithm achieves highest average IoU for 20 sequences {TS. 2,3,5,7,8,9,13,14,16,17,20,22,24,26,27,34,36,37, 38, 39} out of 41. The above sequences cover all the difficulty levels in the dataset.…”
Section: Performance Analysismentioning
confidence: 99%
“…Pose annotations in the dataset are avoided by PGDM which transfer the existing pose estimation model knowledge to pedestrian attribute database. The evaluation uses RAP [17], PETA [18] and PA-100K [19] large scale pedestrian attribute datasets. Given the input image, Part-based Convolutional Baseline (PCB) [13] 1501 [20] dataset.…”
Section: Introductionmentioning
confidence: 99%
“…Researchers are extensively using PETA [18], Market-1501 [20], DukeMTMC-reID [21], CUHK03 [22] and RAP [17] large scale pedestrian datasets for person identification or re-identification. These datasets consist of a gallery of cropped images of persons and annotated soft biometric attributes.…”
Visual appearance-based person retrieval is a challenging problem in surveillance. It uses attributes like height, cloth color, cloth type and gender to describe a human. Such attributes are known as soft biometrics. This paper proposes person retrieval from surveillance video using height, torso cloth type, torso cloth color and gender. The approach introduces an adaptive torso patch extraction and bounding box regression to improve the retrieval. The algorithm uses fine-tuned Mask R-CNN and DenseNet-169 for person detection and attribute classification respectively. The performance is analyzed on AVSS 2018 challenge II dataset and it achieves 11.35% improvement over state-of-the-art based on average Intersection over Union measure.
“…We use RAP-2.0 [32] as our benchmark pedestrian attribute recognition dataset. This dataset contains 84,928 images which were divided into three parts, of which 50,957 for training, 16,986 for validation, and 16,985 for testing.…”
Pedestrian attribute recognition is to predict a set of attribute labels of the pedestrian from surveillance scenarios, which is a very challenging task for computer vision due to poor image quality, continual appearance variations, as well as diverse spatial distribution of imbalanced attributes. It is desirable to model the label dependencies between different attributes to improve the recognition performance as each pedestrian normally possesses many attributes. In this paper, we treat pedestrian attribute recognition as multi-label classification and propose a novel model based on the graph convolutional network (GCN). The model is mainly divided into two parts, we first use convolutional neural network (CNN) to extract pedestrian feature, which is a normal operation processing image in deep learning, then we transfer attribute labels to word embedding and construct a correlation matrix between labels to help GCN propagate information between nodes. This paper applies the object classifiers learned by GCN to the image representation extracted by CNN to enable the model to have the ability to be end-to-end trainable. Experiments on pedestrian attribute recognition dataset show that the approach obviously outperforms other existing state-of-the-art methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.