Multibox Detector Algorithm Research Articles

Traffic flow detection method based on improved SSD algorithm for intelligent transportation system.

With the development of the new generation communication system in China, the application of intelligent transportation system is more extensive, which brings higher demands for vehicle flow detection and monitoring. Traditional traffic flow detection modes often cannot meet the high statistical accuracy requirement and high-speed detection simultaneously. Therefore, an improved Inception module is integrated into the single shot multi box detector algorithm. An intelligent vehicle flow detection model is constructed based on the improved single shot multi box detector algorithm. According to the findings, the convergence speed of the improved algorithm was the fastest. When the test sample was the entire test set, the accuracy and precision values of the improved method were 93.6% and 96.0%, respectively, which were higher than all comparison target detection algorithms. The experimental results of traffic flow statistics showed that the model had the highest statistical accuracy, which converged during the training phase. During the testing phase, except for manual statistics, all methods had the lowest statistical accuracy on motorcycles. The average accuracy and precision of the designed model for various types of images were 96.9% and 96.8%, respectively. The calculation speed of this intelligent model was not significantly improved compared to the other two intelligent models, but it was significantly higher than manual monitoring methods. Two experimental data demonstrate that the intelligent vehicle flow detection model designed in this study has higher detection accuracy. The calculation speed has no significant difference compared with the traditional method, which is helpful to the traffic flow management in intelligent transportation system.

Detection of invasive <italic>Saccharomyces cerevisiae</italic> infections based on convolutional neural network

<p indent="0mm"><italic>Saccharomyces cerevisiae </italic>(<italic>S</italic>.<italic> cerevisiae</italic>) is common in the baking and brewing industries as a fermenting strain and used as a probiotic for preventing and treating various diarrheal and related diseases. However, the cases of invasive <italic>S</italic>.<italic> cerevisiae</italic> infections due to the ingestion of <italic>S</italic>.<italic> cerevisiae</italic> have been increasing over the last two decades, especially in the elderly, immunocompromised, and critically ill patient populations. Additionally, current clinical methods of diagnosing invasive<italic> S</italic>.<italic> cerevisiae</italic> infections are time-consuming, while the optimal times for the diagnosis and early prevention are easily missed. In this paper, a convolutional neural network (CNN)-based object detection method is proposed for the detection and identification of <italic>S</italic>.<italic> cerevisiae</italic> cells in the blood for invasive <italic>S</italic>.<italic> cerevisiae</italic> disease diagnosis. The method is based on the single shot multibox detector algorithm using the ResNet-50 network as a feature extraction network. The experimental results show that the recognition accuracy of the method can reach 97.70%, with a detection time of <sc>0.31 s.</sc> Moreover, the algorithm recognition accuracy showed a significant advantage over three similar CNN algorithms. The paper verifies that the CNN-based object detection method can be a novel method for the detection and diagnosis of invasive <italic>S</italic>.<italic> cerevisiae</italic> infections, and the advantages of high detection accuracy and short method time can achieve early prevention and timely diagnosis of invasive <italic>S</italic>.<italic> cerevisiae</italic> infections.

Individual automatic detection and identification of big cats with the combination of different body parts.

The development of facial recognition technology has become an increasingly powerful tool in wild animal individual recognition. In this paper, we develop an automatic detection and recognition method with the combinations of body features of big cats based on the deep convolutional neural network (CNN). We collected dataset including 12244 images from 47 individual Amur tigers (Panthera tigris altaica) at the Siberian Tiger Park by mobile phones and digital camera and 1940 images and videos of 12 individual wild Amur leopard (Panthera pardus orientalis) by infrared cameras. First, the single shot multibox detector algorithm is used to perform the automatic detection process of feature regions in each image. For the different feature regions of the image, like face stripe or spots, CNNs and multi-layer perceptron models were applied to automatically identify tiger and leopard individuals, independently. Our results show that the identification accuracy of Amur tiger can reach up to 93.27% for face front, 93.33% for right body stripe, and 93.46% for left body stripe. Furthermore, the combination of right face, left body stripe, and right body stripe achieves the highest accuracy rate, up to 95.55%. Consequently, the combination of different body parts can improve the individual identification accuracy. However, it is not the higher the number of body parts, the higher the accuracy rate. The combination model with 3 body parts has the highest accuracy. The identification accuracy of Amur leopard can reach up to 86.90% for face front, 89.13% for left body spots, and 88.33% for right body spots. The accuracy of different body parts combination is lower than the independent part. For wild Amur leopard, the combination of face with body spot part is not helpful for the improvement of identification accuracy. The most effective identification part is still the independent left or right body spot part. It can be applied in long-term monitoring of big cats, including big data analysis for animal behavior, and be helpful for the individual identification of other wildlife species.

Automatic Detection of Medial and Lateral Compartments from Histological Sections of Mouse Knee Joints Using the Single-Shot Multibox Detector Algorithm.

ObjectiveAlthough mouse osteoarthritis (OA) models are widely used, their histological analysis may be susceptible to arbitrariness and inter-examiner variability in conventional methods. Therefore, a method for the unbiased scoring of OA histology is needed. In this study, as the first step for establishing this system, we developed a computer-vision algorithm that automatically detects the medial and lateral compartments of mouse knee sections in a rigorous and unbiased manner.DesignA total of 706 images of coronal sections of mouse knee joints stained by hematoxylin and eosin, safranin O, or toluidine blue were randomly divided into training and validation images at a ratio of 80:20. A model to detect both compartments automatically was built by machine learning using a single-shot multibox detector (SSD) algorithm with training images. The model was tested to determine whether it could accurately detect both compartments by analyzing the validation images and 52 images of sections stained with Picrosirius red, a method not used for the training images.ResultsThe trained model accurately detected both medial and lateral compartments of all 140 validation images regardless of the staining method employed, severity of articular cartilage defects, and the anatomical positions and conditions of the sections. Our model also correctly detected both compartments of 50 of 52 Picrosirius red–stained images.ConclusionsBy applying deep learning based on the SSD algorithm, we successfully developed a model that detects the locations of the medial and lateral compartments of tissue sections of mouse knee joints with high accuracy.

Surface Detection of Solid Wood Defects Based on SSD Improved with ResNet

Due to the lack of forest resources in China and the low detection efficiency of wood surface defects, the output of solid wood panels is not high. Therefore, this paper proposes a method for detecting surface defects of solid wood panels based on a Single Shot MultiBox Detector algorithm (SSD) to detect typical wood surface defects. The wood panel images are acquired by an independently designed image acquisition system. The SSD model included the first five layers of the VGG16 network, the SSD feature mapping layer, the feature detection layer, and the Non-Maximum Suppression (NMS) module. We used TensorFlow to train the network and further improved it on the basis of the SSD network structure. As the basic network part of the improved SSD model, the deep residual network (ResNet) replaced the VGG network part of the original SSD network to optimize the input features of the regression and classification tasks of the predicted bounding box. The solid wood panels selected in this paper are Chinese fir and pine. The defects include live knots, dead knots, decay, mildew, cracks, and pinholes. A total of more than 5000 samples were collected, and the data set was expanded to 100,000 through data enhancement methods. After using the improved SSD model, the average detection accuracy of the defects we obtained was 89.7%, and the average detection time was 90 ms. Both the detection accuracy and the detection speed were improved.

Research on fatigue detection based on visual features

The high incidence of traffic accidents brings immeasurable losses to life. In order to avoid such crises, researchers and automakers have used many methods to solve this problem. Among them, technology based on visual features is widely used in driver fatigue detection. As fatigue detection plays a vital role in the driving process, the high accuracy of fatigue monitoring is very important. This paper focuses on the method based on convolutional neural network to detect driver fatigue. First, in the face detection part, the Single-Shot Multi-Box Detector algorithm is used to improve the speed and accuracy of face detection to extract the eye and mouth regions; second, the VGG16 network is used to learn fatigue features, which is performed on the NTHU-Drowsy Driver Detection (NTHU-DDD) data set and the other two modified data sets Training test. The main result of this work is that the accuracy of fatigue monitoring is higher than other methods including the original method, with an accuracy rate of over 90%. And it has better generalization ability than the multi-physical feature fusion detection method. At the same time, we propose the fatigue detection method based on convolutional neural network to improve the advanced driver assistance system (ADAS) to make it more robust and reliable decision making.

Object detection in real time based on improved single shot multi-box detector algorithm

In today’s scenario, the fastest algorithm which uses a single layer of convolutional network to detect the objects from the image is single shot multi-box detector (SSD) algorithm. This paper studies object detection techniques to detect objects in real time on any device running the proposed model in any environment. In this paper, we have increased the classification accuracy of detecting objects by improving the SSD algorithm while keeping the speed constant. These improvements have been done in their convolutional layers, by using depth-wise separable convolution along with spatial separable convolutions generally called multilayer convolutional neural networks. The proposed method uses these multilayer convolutional neural networks to develop a system model which consists of multilayers to classify the given objects into any of the defined classes. The schemes then use multiple images and detect the objects from these images, labeling them with their respective class label. To speed up the computational performance, the proposed algorithm is applied along with the multilayer convolutional neural network which uses a larger number of default boxes and results in more accurate detection. The accuracy in detecting the objects is checked by different parameters such as loss function, frames per second (FPS), mean average precision (mAP), and aspect ratio. Experimental results confirm that our proposed improved SSD algorithm has high accuracy.

Object Detection System Based on Convolution Neural Networks Using Single Shot Multi-Box Detector

Abstract In this paper we propose object detection technique to detect objects in real time on any device running the model and in any environment. Object detection and training is a vast, vibrant and yet inconclusive and complex area of the computer vision. In this proposed work, convolutional neural network are used to develop a model which is composed of multiple layers to classify the given objects into any of the defined classes. The proposed schemes then use multiple images to detect the objects and label them with their respective class label. These objects are detected by making use of higher resolution feature maps. This is possible because of the recent advancement in deep learning with image processing. These images can be from the video frames which are fed into the model. Our scheme uses separate filters with different default boxes to tackle the difference in aspect ratio and also used multi-scale feature maps for object detection. The training of the model takes place until the error rate is less. The trained model is used to test some sample images. To speed up the computational performance of object detection technique we have use single shot multi-box detector algorithm along with the help of architecture of faster region convolutional neural network. The accuracy in detecting the objects is checked by the different parameters like loss function (LP), mean average precision (mAP), frames per second (FPS).

Real-time long-term correlation tracking by single-shot multibox detection

Long-term robust tracking remains a challenging problem in visual object tracking. Based on the popular tracking-by-detection framework, we propose an approach named real-time long-term correlation tracking by single-shot multibox detection (RLCT-SSD), in which tracking and detection work in parallel and cooperate together. Our algorithm consists of two parts: a tracking module is expected to track in real time and accurately, whereas a detection module is responsible for verifying the tracking results at intervals, and redetecting if necessary. The detector updates the tracking module when the tracking result is unreliable. We introduce a motion model on the basis of fast discriminative scale space tracker to design our tracking module. The detection module is based on the single-shot multibox detector algorithm. To further reduce the computational cost, we use the ShuffleNet as our base network of detection. The experimental results on OTB2013 and OTB2015 demonstrate that our RLCT-SSD performs favorably against most state-of-the-art trackers and achieves long-term accurate tracking running in real time.