A New Multiface Target Detection Algorithm for Students in Class Based on Bayesian Optimized YOLOv3 Model

Deep learning theory is widely used in face recognition. Combined with the needs of classroom attendance and students’ learning status monitoring, this article analyzes the YOLO (You Only Look Once) face recognition algorithms based on regression method. Aiming at the problem of small target missing detection in the YOLOv3 network structure, an improved YOLOv3 algorithm based on Bayesian optimization is proposed. The algorithm uses deep separable convolution instead of conventional convolution to improve the Darknet-53 basic network, and it reduces the amount of calculation and parameters of the network. A multiscale feature pyramid is built, and an attention guidance module is designed to strengthen multiscale fusion, detecting different sizes of targets. The loss function is improved to solve the imbalance of positive and negative sample distribution and the imbalance between simple samples and difficult samples. The Bayesian function is adopted to optimize the classifier and improve the classification efficiency and accuracy, ensuring the accuracy of small target detection. Five groups of comparative experiments are carried out on public COCO and VOC2012 datasets and self-built datasets. The experimental results show that the proposed improved YOLOv3 model can effectively improve the detection accuracy of multiple faces and small targets. Compared with the traditional YOLOv3 model, the mean mAP of the target is improved by more than 1.2%.

Download Full-text

INFRARED SMALL TARGET DETECTION ALGORITHM BASED ON FEATURE SALIENCE AND MULTI-FEATURES FUSION

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001411008579 ◽

2011 ◽

Vol 25 (02) ◽

pp. 299-308 ◽

Cited By ~ 6

Author(s):

ZHEN-XUE CHEN ◽

CHENG-YUN LIU ◽

FA-LIANG CHANG

Keyword(s):

Target Detection ◽

Detection Algorithm ◽

Probability Of Detection ◽

Absolute Difference ◽

Small Target ◽

Probability Of Error ◽

Small Target Detection ◽

Low Snr ◽

Complex Background ◽

Small Targets

It is an important and challenging problem to detect small targets in clutter scene and low SNR (Signal Noise Ratio) in infrared (IR) images. In order to solve this problem, a method based on feature salience is proposed for automatic detection of targets in complex background. Firstly, in this paper, the method utilizes the average absolute difference maximum (AADM) as the dissimilarity measurement between targets and background region to enhance targets. Secondly, minimum probability of error was used to build the model of feature salience. Finally, by computing the realistic degree of features, this method solves the problem of multi-feather fusion. Experimental results show that the algorithm proposed shows better performance with respect to the probability of detection. It is an effective and valuable small target detection algorithm under a complex background.

Download Full-text

Small Target Detection Algorithm Based on Transfer Learning and Deep Separable Network

Journal of Sensors ◽

10.1155/2021/9006288 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Peng Wang ◽

Haiyan Wang ◽

Xiaoyan Li ◽

Lingling Zhang ◽

Ruohai Di ◽

...

Keyword(s):

Transfer Learning ◽

Target Detection ◽

Activation Function ◽

Detection Algorithm ◽

Detection Accuracy ◽

Small Target ◽

Data Set ◽

Small Target Detection ◽

Low Level ◽

Half Axis

With the development of deep learning, target detection from vision sensor has achieved high accuracy and efficiency. However, small target detection remains a challenge due to inadequate use of semantic information and detailed texture information of underlying features. To solve the above problems, this paper proposes a small target detection algorithm based on Mask R-CNN model which integrates transfer learning and deep separable network. Firstly, the feature pyramid fusion structure is introduced to enhance the learning effect of low-level and high-level features, especially to strengthen the information channel of low-level feature and meanwhile optimize the feature information of small target. Secondly, the ELU function is used as the activation function to solve the problem that the original activation function disappears in the negative half axis gradient. Finally, a new loss function F-Softmax combined with Focal Loss was adopted to solve the imbalance of positive and negative sample proportions. In this paper, self-made data set is used to carry out experiments, and the experimental results show that the proposed algorithm makes the detection accuracy of small targets reach 66.5%.

Download Full-text

Dim and Small Target Detection Based on Local Energy Aggregation Degree of Sequence Images

International Journal of Optics ◽

10.1155/2019/9282141 ◽

2019 ◽

Vol 2019 ◽

pp. 1-15

Author(s):

Fan Xiangsuo ◽

Xu Zhiyong

Keyword(s):

Target Detection ◽

Detection Algorithm ◽

Background Modeling ◽

Small Target ◽

Local Energy ◽

Dynamic Scenes ◽

Detection Ability ◽

Small Target Detection ◽

The Difference ◽

Small Targets

In order to improve the detection ability of dim and small targets in dynamic scenes, this paper first proposes an anisotropic gradient background modeling method combined with spatial and temporal information and then uses the multidirectional gradient maximum of neighborhood blocks to segment the difference maps. On the basis of previous background modeling and segmentation extraction candidate targets, a dim small target detection algorithm for local energy aggregation degree of sequence images is proposed. Experiments show that compared with the traditional algorithm, this method can eliminate the interference of noise to the target and improve the detection ability of the system effectively.

Download Full-text

Vehicle Detection in Remote Sensing Image Based on Machine Vision

Computational Intelligence and Neuroscience ◽

10.1155/2021/8683226 ◽

2021 ◽

Vol 2021 ◽

pp. 1-12

Author(s):

Liming Zhou ◽

Chang Zheng ◽

Haoxin Yan ◽

Xianyu Zuo ◽

Baojun Qiao ◽

...

Keyword(s):

Remote Sensing ◽

Target Detection ◽

Detection Algorithm ◽

Detection Methods ◽

Small Target ◽

Remote Sensing Images ◽

Target Feature ◽

Original Algorithm ◽

Wide Range ◽

Small Targets

Target detection in remote sensing images is very challenging research. Followed by the recent development of deep learning, the target detection algorithm has obtained large and fast growth. However, in the application of remote sensing images, due to the small target, wide range, small texture, and complex background, the existing target detection methods cannot achieve people’s hope. In this paper, a target detection algorithm named IR-PANet for remote sensing images of an automobile is proposed. In the backbone network CSPDarknet53, SPP is used to strengthen the learning content. Then, IR-PANet is used as the neck network. After the upper sampling, depthwise separable convolution is used to greatly avoid the lack of small target feature information in the convolution of the shallow network and increase the semantic information in the high-level network. Finally, Gamma correction is used to preprocess the image before image training, which effectively reduces the interference of shadow and other factors on training. The experiment proves that the method has a better effect on small targets obscured by shadows and under the color similar to the background of the picture, and the accuracy is significantly improved based on the original algorithm.

Download Full-text

Infrared Small Target Detection via Modified Random Walks

Remote Sensing ◽

10.3390/rs10122004 ◽

2018 ◽

Vol 10 (12) ◽

pp. 2004 ◽

Cited By ~ 12

Author(s):

Chaoqun Xia ◽

Xiaorun Li ◽

Liaoying Zhao

Keyword(s):

Random Walks ◽

Target Detection ◽

Detection Algorithm ◽

Local Contrast ◽

Small Target ◽

Global Uniqueness ◽

Dimensional Image ◽

Small Target Detection ◽

Small Targets ◽

Infrared Small Target

Infrared small target detection under intricate background and heavy noise is one of the crucial tasks in the field of remote sensing. Conventional algorithms can fail in detecting small targets due to the low signal-to-noise ratios of the images. To solve this problem, an effective infrared small target detection algorithm inspired by random walks is presented in this paper. The novelty of our contribution involves the combination of the local contrast feature and the global uniqueness of the small targets. Firstly, the original pixel-wise image is transformed into an multi-dimensional image with respect to the local contrast measure. Secondly, a reconstructed seeds selection map (SSM) is generated based on the multi-dimensional image. Then, an adaptive seeds selection method is proposed to automatically select the foreground seeds potentially placed in the areas of the small targets in the SSM. After that, a confidence map is constructed using a modified random walks (MRW) algorithm to represent the global uniqueness of the small targets. Finally, we segment the targets from the confidence map by utilizing an adaptive threshold. Extensive experimental evaluation results on a real test dataset demonstrate that our algorithm is superior to the state-of-the-art algorithms in both target enhancement and detection performance.

Download Full-text

Exploring Underwater Target Detection Algorithm Based on Improved SSD

Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University ◽

10.1051/jnwpu/20203840747 ◽

2020 ◽

Vol 38 (4) ◽

pp. 747-754

Author(s):

Wei Qiang ◽

Yuyao He ◽

Yujin Guo ◽

Baoqi Li ◽

Lingjiao He

Keyword(s):

Neural Network ◽

Target Detection ◽

Detection Algorithm ◽

Convolution Neural Network ◽

Detection Accuracy ◽

Detection Model ◽

Underwater Environment ◽

Underwater Target Detection ◽

Basic Network ◽

Underwater Target

As the in-depth exploration of oceans continues, the accurate and rapid detection of fish, bionics and other intelligent bodies in an underwater environment is more and more important for improving an underwater defense system. Because of the low accuracy and poor real-time performance of target detection in the complex underwater environment, we propose a target detection algorithm based on the improved SSD. We use the ResNet convolution neural network instead of the VGG convolution neural network of the SSD as the basic network for target detection. In the basic network, the depthwise-separated deformable convolution module proposed in this paper is used to extract the features of an underwater target so as to improve the target detection accuracy and speed in the complex underwater environment. It mainly fuses the depthwise separable convolution when the deformable convolution acquires the offset of a convolution core, thus reducing the number of parameters and achieving the purposes of increasing the speed of the convolution neural network and enhancing its robustness through sparse representation. The experimental results show that, compared with the SSD detection model that uses the ResNet convolution neural network as the basic network, the improved SSD detection model that uses the depthwise-separated deformable convolution module improves the accuracy of underwater target detection by 11 percentage points and reduces the detection time by 3 ms, thus validating the effectiveness of the algorithm proposed in the paper.

Download Full-text

FE-RetinaNet: Small Target Detection with Parallel Multi-Scale Feature Enhancement

Symmetry ◽

10.3390/sym13060950 ◽

2021 ◽

Vol 13 (6) ◽

pp. 950

Author(s):

Hong Liang ◽

Junlong Yang ◽

Mingwen Shao

Keyword(s):

Target Detection ◽

Semantic Information ◽

Detection Accuracy ◽

Top Down ◽

Scale Feature ◽

Feature Enhancement ◽

Multi Scale ◽

Feature Pyramid ◽

Small Targets ◽

High Level

Because small targets have fewer pixels and carry fewer features, most target detection algorithms cannot effectively use the edge information and semantic information of small targets in the feature map, resulting in low detection accuracy, missed detections, and false detections from time to time. To solve the shortcoming of insufficient information features of small targets in the RetinaNet, this work introduces a parallel-assisted multi-scale feature enhancement module MFEM (Multi-scale Feature Enhancement Model), which uses dilated convolution with different expansion rates to avoid multiple down sampling. MFEM avoids information loss caused by multiple down sampling, and at the same time helps to assist shallow extraction of multi-scale context information. Additionally, this work adopts a backbone network improvement plan specifically designed for target detection tasks, which can effectively save small target information in high-level feature maps. The traditional top-down pyramid structure focuses on transferring high-level semantics from the top to the bottom, and the one-way information flow is not conducive to the detection of small targets. In this work, the auxiliary MFEM branch is combined with RetinaNet to construct a model with a bidirectional feature pyramid network, which can effectively integrate the strong semantic information of the high-level network and high-resolution information regarding the low level. The bidirectional feature pyramid network designed in this work is a symmetrical structure, including a top-down branch and a bottom-up branch, performs the transfer and fusion of strong semantic information and strong resolution information. To prove the effectiveness of the algorithm FE-RetinaNet (Feature Enhancement RetinaNet), this work conducts experiments on the MS COCO. Compared with the original RetinaNet, the improved RetinaNet has achieved a 1.8% improvement in the detection accuracy (mAP) on the MS COCO, and the COCO AP is 36.2%; FE-RetinaNet has a good detection effect on small targets, with APs increased by 3.2%.

Download Full-text

Animation Character Detection Algorithm Based on Clustering and Cascaded SSD

Scientific Programming ◽

10.1155/2022/4223295 ◽

2022 ◽

Vol 2022 ◽

pp. 1-10

Author(s):

Yuan Wang

Keyword(s):

Big Data ◽

Clustering Algorithm ◽

Detection Algorithm ◽

Detection Accuracy ◽

Small Target ◽

Animation Industry ◽

And Performance ◽

Small Targets ◽

High Level ◽

Detection Effect

With the evolution of the Internet and information technology, the era of big data is a new digital one. Accordingly, animation IP has been more and more widely welcomed and concerned with the continuous development of the domestic and international animation industry. Hence, animation video analysis will be a good landing application for computers. This paper proposes an algorithm based on clustering and cascaded SSD for object detection of animation characters in the big data environment. In the training process, the improved classification Loss function based on Focal Loss and Truncated Gradient was used to enhance the initial detection effect. In the detection phase, this algorithm designs a small target enhanced detection module cascaded with an SSD network. In this way, the high-level features corresponding to the small target region can be extracted separately to detect small targets, which can effectively enhance the detection effect of small targets. In order to further improve the effect of small target detection, the regional candidate box is reconstructed by a k-means clustering algorithm to improve the detection accuracy of the algorithm. Experimental results demonstrate that this method can effectively detect animation characters, and performance indicators are better than other existing algorithms.

Download Full-text