PFF-FPN: A Parallel Feature Fusion Module Based on FPN in Pedestrian Detection

Yang, Guangqing; Wang, Zhengyou; Zhuang, Shanna

doi:10.1109/icceai52939.2021.00075

Cited by 13 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shallow feature maps maintain rich shallow features of images, such as their morphology, size, and other features, whereas deep feature maps preserve semantic information, such as contextual information and location relationships [25,26]. Better detection performance can be achieved by fusing the feature maps of the different phases.…”

Section: B Feature Pyramid Networkmentioning

confidence: 99%

A Locating Approach for Small-Sized Components of Railway Catenary Based on Improved YOLO With Asymmetrically Effective Decoupled Head

Feng

Fei

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In the routine inspection process of railway catenary systems, the primary task is to find out the locations of various components accurately. The complex composition of the components in the catenary system and their large dimensional differences make the inspection of small components considerably difficult. Aiming at the problem of the difficulty in locating small components, a new locating method, named asymmetrically effective decoupled head-you only look once (AED-YOLO), for locating small components of the catenary has been proposed in this study. In this method, firstly, a small object detection layer has been added to improve the detection accuracy of the small-sized components such as fastener nuts and bracing wire. Secondly, to reduce missed and false detection errors of small components, the improved bidirectional feature pyramid network with high-order spatial interactions and recursive gated convolution has been used to fuse the features of different scales to further enhance the ability to detect small objects. Finally, an asymmetrically effective decoupled head has been proposed using different decoupled branches to decouple the classification and localization processes, thus further reducing the error in small-sized object classification and location. Experiments performed on the railway catenary dataset collected on-site show that the proposed localization method can efficiently improve detection accuracy, achieving a mean average precision of 93.5%. Thus, compared to the other methods, the proposed method can accurately locate small-sized components.

show abstract

Section: B Feature Pyramid Networkmentioning

confidence: 99%

A Locating Approach for Small-Sized Components of Railway Catenary Based on Improved YOLO With Asymmetrically Effective Decoupled Head

Feng

Fei

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The feature maps at different scales contain sometimes conflicting information about the size of target instances, which can interfere with the calculation of gradients during the training of the network and reduce the effectiveness of the feature pyramids. To avoid losing important information during the feature fusion process, Guiyi Yang et al proposed a new model based on FPN, called PFF-FPN, which chose to use three different FPN structures to pass features and fuse the feature information of the corresponding layers to enhance the important information [28]. Golnaz Ghaisi et al also proposed a new feature pyramid network structure based on FPN called NAS-FPN, which solves the large-scale search space problem in feature pyramids by combining a scalable search space with a neural combination search algorithm [29].…”

Section: Improvements To the Feature Fusion Part Of The Baseline Modelmentioning

confidence: 99%

An Improved Yolov5 for Multi-Rotor UAV Detection

Liu

Luo

2022

Electronics

View full text Add to dashboard Cite

Multi-rotor drones have a wide range of applications in practical scenarios; however, the use of multi-rotor drones for illegal acts is also on the rise, in order to improve the recognition accuracy of multi-rotor drones. A new multi-rotor drone detection algorithm is proposed. Firstly, the Yolov5 backbone is replaced with Efficientlite, thus reducing the number of parameters in the model. Secondly, adaptively spatial feature fusion is injected into the head of the baseline model to facilitate the fusion of feature maps with different spatial resolutions, in order to balance the accuracy loss caused by the lightweight of the model backbone. Finally, a constraint of angle is introduced into the original regression loss function to avoid the mismatch between the prediction frame and the real frame orientation during the training process in order to improve the speed of network convergence. Experiments show that the improved Yolov5s exhibits better detection performance, which provides a superior method for detecting multi-rotor UAVs in real-world scenarios.

show abstract

“…Multiscale feature fusion has been widely used in object detection algorithms, and it effectively improves detection accuracy. The current multiscale feature fusion structures mainly include FPN, PAN, and their variants 40,41 . Based on PAN, this paper designs two different multiscale feature fusion structures according to different needs.…”

Section: Miniyolomentioning

confidence: 99%

“…The current multiscale feature fusion structures mainly include FPN, PAN, and their variants. 40,41 Based on PAN, this paper designs two different multiscale feature fusion structures according to different needs.…”

Section: Multibranch Blockmentioning

confidence: 99%

MiniYOLO: A lightweight object detection algorithm that realizes the trade‐off between model size and detection accuracy

Liu

Zhang

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

The object detection task is to locate and classify objects in an image. The current state‐of‐the‐art high‐accuracy object detection algorithms rely on complex networks and high computational cost. These algorithms have high requirements on the memory resource and computing capability of the deployed device, and are difficult to apply to mobile and embedded devices. Through the depthwise separable convolution and multiple efficient network structures, this paper designs a lightweight backbone network and two different multiscale feature fusion structures, and proposes a lightweight one‐stage object detection algorithm—MiniYOLO. With the model size of only 4.2 MB, MiniYOLO still maintains a high detection accuracy, realizing the trade‐off between the model size and detection accuracy. Experimental results on MS COCO 2017 data set show that compared to the state‐of‐the‐art PP‐YOLO‐tiny, MiniYOLO achieves higher mAP with the same model size. Compared with other lightweight object detection algorithms, MiniYOLO has certain advantages in detection accuracy or model size. The code associated with this paper can be downloaded from https://github.com/CaedmonLY/MiniYOLO.

show abstract

PFF-FPN: A Parallel Feature Fusion Module Based on FPN in Pedestrian Detection

Cited by 13 publications

References 13 publications

A Locating Approach for Small-Sized Components of Railway Catenary Based on Improved YOLO With Asymmetrically Effective Decoupled Head

A Locating Approach for Small-Sized Components of Railway Catenary Based on Improved YOLO With Asymmetrically Effective Decoupled Head

An Improved Yolov5 for Multi-Rotor UAV Detection

MiniYOLO: A lightweight object detection algorithm that realizes the trade‐off between model size and detection accuracy

Contact Info

Product

Resources

About