JCS-Net: Joint Classification and Super-Resolution Network for Small-Scale Pedestrian Detection in Surveillance Images

Pang, Yanwei; Cao, Jiale; Wang, Jian; Han, Jungong

doi:10.1109/tifs.2019.2916592

Cited by 91 publications

(44 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the actual underwater environment, multi-AUV is subject to environmental interference at any time during information collection, such as turbid water quality, uneven light, target occlusion, complex background, and overlapping targets. The algorithm in this paper simulates the above influencing factors, compared with the algorithm R-FCN [30], Faster R-CNN [31], JCS-Net [32], OHEM [33], FP-SSD [34], YOLO [35] Compare. The basic settings of each algorithm are shown in Table 4.…”

Section: Experimental Results and Analysesmentioning

confidence: 99%

Multi-AUV Collaborative Target Recognition Based on Transfer-Reinforcement Learning

Cai

Sun

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Due to the existence of unfavorable factors such as turbid water quality and target occlusion, it is difficult to obtain valid data of target features. Due to the repeated calculation of similar data, the real-time performance of the algorithm is poor. In view of the above problems, this paper proposes a multi-AUV collaborative target recognition method based on transfer-reinforcement learning. The features of the target information which is collected by multi-AUV are fused based on wavelet transformation and affine invariance. The similarity of features is calculated by Mahalanobis distance and the learning model is selected autonomously based on the similarity threshold. Based on the Q-learning reinforcement learning model, the target information under the interference environment is trained intensively, and the effective features are extracted and stored in the source domain, which can reduce the impact of the environmental interference on the target recognition. The feature transfer learning model based on deep confidence network transfers the feature data of the source domain to the target domain, reducing the repeated calculation of similar data, and then ensuring the real-time performance of the algorithm. Simulation experiments are conducted in the SUN dataset under five underwater environments (turbid water, target occlusion, insufficient light, complex background, and overlapping targets), and the results demonstrate that the proposed model achieves better performance.

show abstract

Section: Experimental Results and Analysesmentioning

confidence: 99%

Multi-AUV Collaborative Target Recognition Based on Transfer-Reinforcement Learning

Cai

Sun

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Some methods [46], [3], [2], [42] use semantic information to improve pedestrian detection. Some methods [58], [8], [52], [66] aim to improve small-scale pedestrian detection, while some methods [78], [83], [51] exploit the part or visible information for occluded pedestrian detection. To improve pedestrian detection in crowded scenes, some methods [63], [45], [33], [11] exploit how to combine the highly overlapping bounding boxes.…”

Section: B the Methods Of Object Detectionmentioning

confidence: 99%

TJU-DHD: A Diverse High-Resolution Dataset for Object Detection

Pang

Cao

et al. 2021

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Vehicles, pedestrians, and riders are the most important and interesting objects for the perception modules of selfdriving vehicles and video surveillance. However, the state-of-theart performance of detecting such important objects (esp. small objects) is far from satisfying the demand of practical systems. Large-scale, rich-diversity, and high-resolution datasets play an important role in developing better object detection methods to satisfy the demand. Existing public large-scale datasets such as MS COCO collected from websites do not focus on the specific scenarios. Moreover, the popular datasets (e.g., KITTI and Citypersons) collected from the specific scenarios are limited in the number of images and instances, the resolution, and the diversity. To attempt to solve the problem, we build a diverse high-resolution dataset (called TJU-DHD). The dataset contains 115,354 high-resolution images (52% images have a resolution of 1624×1200 pixels and 48% images have a resolution of at least 2,560×1,440 pixels) and 709,330 labeled objects in total with a large variance in scale and appearance. Meanwhile, the dataset has a rich diversity in season variance, illumination variance, and weather variance. In addition, a new diverse pedestrian dataset is further built. With the four different detectors (i.e., the one-stage RetinaNet, anchor-free FCOS, two-stage FPN, and Cascade R-CNN), experiments about object detection and pedestrian detection are conducted. We hope that the newly built dataset can help promote the research on object detection and pedestrian detection in these two scenes. The dataset is available at https://github.com/tjubiit/TJU-DHD.

show abstract

“…This model combines two types of matrix loop kernels, and makes full use of the complementary features of color and HOG features to learn robust target representation. Pang et al [29] proposed a unified network (called JCS-Net) for small-scale pedestrian detection based on HOG + LUV and JCS-Net, which constructs a multi-layer channel feature (MCF) to train detectors. Qu et al [30] proposed a machine learning algorithm for texture information extraction from through-focus scanning optical microscopy (TSOM) images.…”

Section: Related Workmentioning

confidence: 99%

A Novel Changing Athlete Body Real-Time Visual Tracking Algorithm Based on Distractor-Aware SiamRPN and HOG-SVM

et al. 2020

View full text Add to dashboard Cite

Athlete detection in sports videos is a challenging task due to the dynamic and cluttered background. Distractor-aware SiamRPN (DaSiamRPN) has a simple network structure and can be utilized to perform long-term tracking of large data sets. However, similarly to the Siamese network, the tracking results heavily rely on the given position in the initial frame. Hence, there is a lack of solutions for some complex tracking scenarios, such as running and changing of bodies of athletes, especially in the stage from squatting to standing to running. The Haar feature-based cascade classifier is involved to catch the key frame, representing the video frame of the most dramatic changes of the athletes. DaSiamRPN is implemented as the tracking method. In each frame after the key frame, a detection window is given based on the bounding box generated by the DaSiamRPN tracker. In the new detection window, a fusion method (HOG-SVM) combining features of Histograms of Oriented Gradients (HOG) and a linear Support-Vector Machine (SVM) is proposed for detecting the athlete, and the tracking results are updated in real-time by fusing the tracking results of DaSiamRPN and HOG-SVM. Our proposed method has reached a stable and accurate tracking effect in testing on men’s 100 m video sequences and has realized real-time operation.

show abstract

JCS-Net: Joint Classification and Super-Resolution Network for Small-Scale Pedestrian Detection in Surveillance Images

Abstract: Please refer to published version for the most recent bibliographic citation information. If a published version is known of, the repository item page linked to above, will contain details on accessing it.

Cited by 91 publications

References 61 publications

Multi-AUV Collaborative Target Recognition Based on Transfer-Reinforcement Learning

Multi-AUV Collaborative Target Recognition Based on Transfer-Reinforcement Learning

TJU-DHD: A Diverse High-Resolution Dataset for Object Detection

A Novel Changing Athlete Body Real-Time Visual Tracking Algorithm Based on Distractor-Aware SiamRPN and HOG-SVM

Contact Info

Product

Resources

About