Robust Head Detection in Complex Videos Using Two-Stage Deep Convolution Framework
19 May 2020-IEEE Access (Institute of Electrical and Electronics Engineers (IEEE))-Vol. 8, pp 98679-98692
TL;DR: This paper presents a two-stage head detection framework that utilizes fully convolutional network (FCN) to generate scale-aware proposals followed by CNN that classifies each proposal into two classes, i.e. head and background.
Abstract: Pedestrian head detection plays an important role in identifying and localizing individuals in real world visual data. Head detection is a nontrivial problem due to considerable variance in camera view-points, scales, human poses, and appearances in the scene. Thanks to the translation invariance property of convolutional neural networks (CNNs) which enables large capacity CNNs to handle the problem of appearance and pose variations in the scene. However, the problem of scale invariance is still an open issue. To address this problem, this paper presents a two-stage head detection framework that utilizes fully convolutional network (FCN) to generate scale-aware proposals followed by CNN that classifies each proposal into two classes, i.e. head and background. Experiments results show that using scale-aware proposals obtained by FCN, the object recall rate and mean average precision (mAP) are improved. Additionaly, we demonstrate that our framework achieved state-of-the-art results on four challenging benchmark datasets, i.e. HollywoodHeads, Casablanca, SHOCK, and WIDERFACE.
Citations
More filters
TL;DR: In this paper, the authors developed a new approach based on two parallel Deeplapv3+ to improve the performance of the person detection system, which can be used not only for the detection of the human head but also for several semantic segmentation applications.
Abstract: In the field of computer vision, object detection consists of automatically finding objects in images by giving their positions. The most common fields of application are safety systems (pedestrian detection, identification of behavior) and control systems. Another important application is head/person detection, which is the primary material for road safety, rescue, surveillance, etc. In this study, we developed a new approach based on two parallel Deeplapv3+ to improve the performance of the person detection system. For the implementation of our semantic segmentation model, a working methodology with two types of ground truths extracted from the bounding boxes given by the original ground truths was established. The approach has been implemented in our two private datasets as well as in a public dataset. To show the performance of the proposed system, a comparative analysis was carried out on two deep learning semantic segmentation state-of-art models: SegNet and U-Net. By achieving 99.14% of global accuracy, the result demonstrated that the developed strategy could be an efficient way to build a deep neural network model for semantic segmentation. This strategy can be used, not only for the detection of the human head but also be applied in several semantic segmentation applications.
5 citations
TL;DR: Wang et al. as discussed by the authors proposed a novel fusion framework for occupancy detection and estimation based on two different perspectives: head detection method combined with indoor scene knowledge to filter false positives and recover missed detection, and a two-vision entrance counting method to refine the predicted results.
3 citations
TL;DR: Wang et al. as mentioned in this paper proposed Motion-aware Pseudo-Siamese Network (MPSN), an end-to-end approach that leverages head motion information to guide deep learning models to extract effective head features in indoor scenarios.
2 citations
Posted Content•
TL;DR: Wang et al. as discussed by the authors proposed Motion-aware Pseudo Siamese Network (MPSN), which leverages head motion information to guide the deep model to extract effective head features in indoor scenarios.
Abstract: Head detection in the indoor video is an essential component of many real-world applications. While deep models have achieved remarkable progress in general object detection, they are not satisfying enough in complex indoor scenes. The indoor surveillance video often includes cluttered background objects, among which heads have small scales and diverse poses. In this paper, we propose Motion-aware Pseudo Siamese Network (MPSN), an end-to-end approach that leverages head motion information to guide the deep model to extract effective head features in indoor scenarios. By taking the pixel-wise difference of adjacent frames as the auxiliary input, MPSN effectively enhances human head motion information and removes the irrelevant objects in the background. Compared with prior methods, it achieves superior performance on the two indoor video datasets. Our experiments show that MPSN successfully suppresses static background objects and highlights the moving instances, especially human heads in indoor videos. We also compare different methods to capture head motion, which demonstrates the simplicity and flexibility of MPSN. Finally, to validate the robustness of MPSN, we conduct adversarial experiments with a mathematical solution of small perturbations for robust model selection. Code is available at https://github.com/pl-share/MPSN.
TL;DR: Zhang et al. as mentioned in this paper proposed two modules for enhancing useful feature extraction in the SA layer to improve 3D object detection accuracy, focusing on the foreground and boundary scores of the points and reweighing the Furthest Point Sampling (FPS) using the evaluated scores.
References
More filters
Proceedings Article•
03 Dec 2012TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
73,978 citations
Proceedings Article•
04 Sep 2014TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
55,235 citations
"Robust Head Detection in Complex Vi..." refers methods in this paper
...We use different state-of-the-art network architectures, like AlexNet [19], VGGS [4], VGG-verydeep-16 [38] and ZF [54]for classification....
[...]
...For the classification, we use different architectures, AlexNet [19], VGGS [4], VGG-verydeep-16 [38], and ZF [54]....
[...]
Proceedings Article•
01 Jan 2015TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
49,914 citations
07 Jun 2015
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Abstract: Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet [20], the VGG net [31], and GoogLeNet [32]) into fully convolutional networks and transfer their learned representations by fine-tuning [3] to the segmentation task. We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes less than one fifth of a second for a typical image.
28,225 citations
27 Jun 2016
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Abstract: We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
27,256 citations
"Robust Head Detection in Complex Vi..." refers methods in this paper
...YOLO beast Faster-RCNN in terms of inference speed on most of existing object detection datasets, however, at the cost of accuracy....
[...]
...You only look once (YOLO) [30] generates bounding boxes using regression and classify each bounding box by assigning class scores to the bounding boxes....
[...]
...[31] J. Redmon and A. Farhadi, ‘‘YOLO9000: Better, faster, stronger,’’ in Proc....
[...]