An Improved Aggregated-Mosaic Method for the Sparse Object Detection of Remote Sensing Imagery

Zhao, Boya; Wu, Yuanfeng; Guan, Xinran; Gao, Lianru; Zhang, Bing

doi:10.3390/rs13132602

Cited by 20 publications

(7 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Key enhancements to the YOLOv5s algorithm include data augmentation using Mosaic 25 , 26 , adaptive anchor box calculations, and adaptive image scaling. The backbone employs operations such as convolution and pooling to reduce feature map dimensions, increase depth, and incorporate the CBAM C3 module for automatic attention to image features.…”

Section: Methodsmentioning

confidence: 99%

Machine vision-based autonomous road hazard avoidance system for self-driving vehicles

Qiu,

Tang,

Yang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The resolution of traffic congestion and personal safety issues holds paramount importance for human’s life. The ability of an autonomous driving system to navigate complex road conditions is crucial. Deep learning has greatly facilitated machine vision perception in autonomous driving. Aiming at the problem of small target detection in traditional YOLOv5s, this paper proposes an optimized target detection algorithm. The C3 module on the algorithm’s backbone is upgraded to the CBAMC3 module, introducing a novel GELU activation function and EfficiCIoU loss function, which accelerate convergence on position loss lbox, confidence loss lobj, and classification loss lcls, enhance image learning capabilities and address the issue of inaccurate detection of small targets by improving the algorithm. Testing with a vehicle-mounted camera on a predefined route effectively identifies road vehicles and analyzes depth position information. The avoidance model, combined with Pure Pursuit and MPC control algorithms, exhibits more stable variations in vehicle speed, front-wheel steering angle, lateral acceleration, etc., compared to the non-optimized version. The robustness of the driving system's visual avoidance functionality is enhanced, further ameliorating congestion issues and ensuring personal safety.

show abstract

Section: Methodsmentioning

confidence: 99%

Machine vision-based autonomous road hazard avoidance system for self-driving vehicles

Qiu,

Tang,

Yang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Combining the features of pixel domain and compressed domain can improve the accuracy of target detection. Get a more accurate traffic target [18,19]. It also uses a multilayer sensor to capture a moving target.…”

Section: Moving Object Detection Algorithm Based On Ffmpeg Codecmentioning

confidence: 99%

Analysis of Art Classroom Teaching Behavior Based on Intelligent Image Recognition

Chi-hui

2022

Mobile Information Systems

View full text Add to dashboard Cite

To solve the problem of intelligent image recognition in classroom behavior, this paper proposes a fast target detection based on FFmpeg CODEC, extracts MHI-HOG joint features according to the located foreground target area, and finally completes the behavior recognition model through a BP neural network support vector machine joint classifier based on the look-up table. The results are as follows: the motion detection method based on H.264 FFmpeg CODEC video has the highest detection accuracy, which can reach 95%. The foreground detection method takes about 10 ms and saves 90% of the time. The behavior classification and recognition effect of MHI-HOG joint features based on the model has been significantly improved, and the comprehensive recognition rate has reached 95%. The built-in BP neural network support vector machine has 97% accuracy in extracting, classifying, and recognizing the characteristics of a single sample. This study attempts to identify and analyze the class behavior and validate the effectiveness of the collaborative classifiers proposed in this paper to build an intellectual classroom.

show abstract

“…Feature Learning. The representatives of feature learning are supervised CNNs [25]- [27] and unsupervised autoencoder(AE)/GAN networks [28], [29], whose perfect training relies on enough and strong prior samples. The core insight of this anomaly detection paradigm is to capture the intrinsic geometric distribution (i.e., semantic features) of spectral vectors via hierarchical data-driven feature embedding.…”

Section: Metricsmentioning

confidence: 99%

Learning-Free Hyperspectral Anomaly Detection With Unpredictive Frequency Residual Priors

Zhou

Wang

Gao

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Hyperspectral anomaly detection aims to fast and credibly find nontrivial candidate targets without prior knowledge, which has become an increasingly pressing need as imagery swath and resolution are growing rapidly. Relevant state-of-the-art learning-based anomaly detection approaches have benefited from data-driven hierarchical feature embeddings that typically model the geometric distribution of spectral vectors. However, most of these techniques are incompatible with resource-constrained applications: 1) huge computational costs caused by feedforward convolution operation cannot be supported with limited computation resources and storage (e.g., in-orbit processing); 2) detection accuracy relies on large-scale training datasets, which results in labor-expensive imagery collection, pixel-level labeling, and timeconsuming learning procedure. To address these issues, we advocate a learning-free, frequency domain anomaly detection method combined with predictive coding, an intriguing heuristic prior from human vision system. Technically, 1) inherently efficient frequency transformation could be implemented with existing image compression modules (e.g., JPEG or JPEG2000 codec), which improves the utilization of computational resources; 2) predictive coding mechanism is exploited for suppressing frequently occurring information represented in the low-entropy frequency domain, such that the "unpredictive" subject (i.e., anomaly spectrums) can "pop out" with naive residuals. Such heuristic prior incorporated into the computational model can reduce dependence on the large-scale training set. Experiments on real-world hyperspectral datasets confirm the efficacy of our model. Besides, low computation cost of the proposed (fast frequency transformation and analytical solutions) anomaly detector facilitates rather straightforward sliding window verification in high-resolution imagery.

show abstract

An Improved Aggregated-Mosaic Method for the Sparse Object Detection of Remote Sensing Imagery

Cited by 20 publications

References 44 publications

Machine vision-based autonomous road hazard avoidance system for self-driving vehicles

Machine vision-based autonomous road hazard avoidance system for self-driving vehicles

Analysis of Art Classroom Teaching Behavior Based on Intelligent Image Recognition

Learning-Free Hyperspectral Anomaly Detection With Unpredictive Frequency Residual Priors

Contact Info

Product

Resources

About