An enhanced SSD with feature cross-reinforcement for small-object detection

Gong, Lixiong; Huang, Xiao; Chao, Yinkang; Chen, Jialin; Lei, Binwen

doi:10.1007/s10489-023-04544-1

Cited by 11 publications

(2 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Small target detection presents significant challenges within the realm of target detection, necessitating algorithms with robust fine feature extraction capabilities (Shamsolmoali et al, 2022;Gong, 2023). Typically, two primary criteria are employed to define small targets: absolute size and relative size.…”

Section: Small Target Detectionmentioning

confidence: 99%

Enhanced YOLOv7 integrated with small target enhancement for rapid detection of objects on water surfaces

Yu,

Zheng,

Xie

et al. 2023

Front. Neurorobot.

View full text Add to dashboard Cite

Unmanned surface vessel (USV) target detection algorithms often face challenges such as misdetection and omission of small targets due to significant variations in target scales and susceptibility to interference from complex environments. To address these issues, we propose a small target enhanced YOLOv7 (STE-YOLO) approach. Firstly, we introduce a specialized detection branch designed to identify tiny targets. This enhancement aims to improve the multi-scale target detection capabilities and address difficulties in recognizing targets of different sizes. Secondly, we present the lite visual center (LVC) module, which effectively fuses data from different levels to give more attention to small targets. Additionally, we integrate the lite efficient layer aggregation networks (L-ELAN) into the backbone network to reduce redundant computations and enhance computational efficiency. Lastly, we use Wise-IOU to optimize the loss function definition, thereby improving the model robustness by dynamically optimizing gradient contributions from samples of varying quality. We conducted experiments on the WSODD dataset and the FIOW-Img dataset. The results on the comprehensive WSODD dataset demonstrate that STE-YOLO, when compared to YOLOv7, reduces network parameters by 14% while improving AP50 and APs scores by 2.1% and 1.6%, respectively. Furthermore, when compared to five other leading target detection algorithms, STE-YOLO demonstrates superior accuracy and efficiency.

show abstract

Section: Small Target Detectionmentioning

confidence: 99%

Enhanced YOLOv7 integrated with small target enhancement for rapid detection of objects on water surfaces

Yu,

Zheng,

Xie

et al. 2023

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…Convolutional neural network (CNN)-based feature extraction methods can effectively extract both low-level and high-level features, realizing automatic extraction of image features, and therefore have high detection accuracy and speed, which is more advantageous compared to traditional image processing techniques. Although CNN-based object detection methods are developing rapidly, most of them have been developed for different objects in an image (e.g., recognizing a dog or a cat) [4][5][6][7]. However, valve-like object detection is quite different from previous applications.…”

Section: Introductionmentioning

confidence: 99%

Multi-path Hybrid Attention Deep Neural Network for Valve Detection

Zhang,

Huang,

2024

Preprint

View full text Add to dashboard Cite

Valves Detection is a basic function of rescue robots in various disaster situations. However, due to the small differences between similar valves, rescue robots suffer great challenges in valve detection in complex environments. To address this challenge, this paper proposes a multi-path hybrid attention deep neural network (MHADNN). By weighting features at different scales and spatial positions, the MHADNN can help valve detection models focus on more discriminative subtle features, thereby enhancing the ability to distinguish similar valves. This paper combines the MHADNN with the YOLOv5n to develop a valve detection model. The comparative experiments are conducted on a similar valve dataset collected in the simulated environment of a chemical industrial park. The experimental results show that compared with YOLOv5n, the proposed valve detection model has an average precision improvement of 4.20%. It has excellent performance in distinguishing similar valves.

show abstract

I-YOLO: a novel single-stage framework for small object detection

Tong,

2024

Vis Comput

View full text Add to dashboard Cite

An enhanced SSD with feature cross-reinforcement for small-object detection

Cited by 11 publications

References 57 publications

Enhanced YOLOv7 integrated with small target enhancement for rapid detection of objects on water surfaces

Enhanced YOLOv7 integrated with small target enhancement for rapid detection of objects on water surfaces

Multi-path Hybrid Attention Deep Neural Network for Valve Detection

I-YOLO: a novel single-stage framework for small object detection

Contact Info

Product

Resources

About