Multi-Scale Person Localization With Multi-Stage Deep Sequential Framework

Abstract

Person detection in real videos and images is a classical research problem in computer vision. Person detection is a nontrivial problem that offers many challenges due to several nuisances that commonly observed in natural videos. Among these, scale is the main challenging problem in various object detection tasks. To solve the scale problem, we propose a framework that estimates the scales of person's heads, as we argue that head is the only visible part in complex scenes. we propose a head detection framework that explicitly handles head scales. The framework consists of two sequential networks: (1) scale estimation network (SENet) and (2) head detection network. SENet predicts the distribution of scales from the input image in the form of histogram. Then the scale histogram adjust anchor scale set of region proposal network that generates object proposals. These objects proposals are then classified into two classes, that is, head and background by the detection network. We evaluate proposed framework on three challenging benchmark datasets. Experiment results show that proposed framework achieves state-of-the-art performance.

An Accurate Detection Model of Takifugu rubripes Using an Improved YOLO-V7 Network

“…This paper improved the detection head of the original YOLO-V7, abandoned the feature map of the original, and deepened it based upon the last feature extraction. Through this, the progressive information flow, multi-scale problem [39,40], and inadequate extraction of the small target information were effectively solved during the detection. The results of the enhanced comparative experiment are shown in Figure 8.…”

Exploiting the Multiscale Information Fusion Capabilities for Aiding the Leukemia Diagnosis Through White Blood Cells Segmentation

“…In MIF-Net, IIF ensures feature empowerment after intervals whereas EIF helps in improved boundary predictions for cytoplasm and nucleus. Multi-scale information fusion is being widely used in different deep learning-based applications [45], [46]. In [45], a scale estimation network (SENet) with head detection network is presented for person localization.…”

“…Multi-scale information fusion is being widely used in different deep learning-based applications [45], [46]. In [45], a scale estimation network (SENet) with head detection network is presented for person localization. SENet employs ResNet-101 as the backbone to address the problem of vanishing gradient.…”

“…FPN is used with the backbone of ResNet. MIF-Net is an entirely different architecture compared with [45] and [46], some of the major differences are highlighted in Table 2. In MIF-Net, a maximum of 256 channels are used which results in a small number of parameters requirement.…”

“…Subsequently, only three downsampling operations are performed in MIF-Net to keep the final feature map size sufficiently large for avoiding minor information loss. Unlike [45], [46], the proposed method uses a total of 7 fusion operations including EIF and IIF. In the proposed method, spatial information is splitted from the initial layer.…”