Improved SSD-Based Multi-scale Pedestrian Detection Algorithm

Deep learning techniques help computer vision automatically learn the intrinsic patterns within complex data. This research mainly concentrates on creating a mobile application based on augmented reality for elderly mobile users that helps in identifying the traffic signals and other signboards in real‐time using deep learning techniques. TensorFlow serves as an implementation platform to build the object detection system with deep learning. The single shot multibox detector (SSD) model and the two‐stage faster‐regional convolutional neural network (RCNN) models from TensorFlow's object detection application programming interface (API) are compared in this study. The SSD model with MobileNet as a backbone network serves well for this study as it is faster than the RCNN model with comparable accuracy. However, unconstrained environments like occlusions can be an obstacle to the effective performance of an object detection system. This research provides a solution to handle occlusions by developing a robust object detection system through image segmentation techniques. The model introduced is based on the SSD MobileNet model which enables it to be deployable on mobile devices for real‐time offline detection. The developed model exhibits faster performance than the state‐of‐the‐art instance segmentation model, Mask RCNN with comparable accuracy. Elaborated implementation of this system and results are presented in further sections.

This paper studies the problems of vehicle make & model classification. Some of the main challenges are reaching high classification accuracy and reducing the annotation time of the images. To address these problems, we have created a fine-grained database using online vehicle marketplaces of Turkey. A pipeline is proposed to combine an SSD (Single Shot Multibox Detector) model with a CNN (Convolutional Neural Network) model to train on the database. In the pipeline, we first detect the vehicles by following an algorithm which reduces the time for annotation. Then, we feed them into the CNN model. It is reached approximately 4% better classification accuracy result than using a conventional CNN model. Next, we propose to use the detected vehicles as ground truth bounding box (GTBB) of the images and feed them into an SSD model in another pipeline. At this stage, it is reached reasonable classification accuracy result without using perfectly shaped GTBB. Lastly, an application is implemented in a use case by using our proposed pipelines. It detects the unauthorized vehicles by comparing their license plate numbers and make & models. It is assumed that license plates are readable.

Aiming at the problem of target frame redundancy in the original Single Shot MultiBox Detector (SSD) model, this paper proposes a Cervical epithelial cell recognition based on improved SSD. The algorithm uses the mask to extract the ROI region, and preprocesses the original image, so that the computational complexity of the extracted image features is greatly reduced, and then the resnet network is used to replace the original VGG network. Finally, the modified SSD model is used to perform cervical epithelial cells. Identify and accurately locate. The algorithm proposed in this paper can accurately and quickly excavate the characteristics of cervical epithelial cells under microscope, and effectively improve the recognition speed and target positioning accuracy.

The timely and accurate mapping and monitoring of mine tailings dams is crucial to the improvement of management practices by decision makers and to the prevention of disasters caused by failures of these dams. Due to the complex topography, varying geomorphological characteristics, and the diversity of ore types and mining activities, as well as the range of scales and production processes involved, as they appear in remote sensing imagery, tailings dams vary in terms of their scale, color, shape, and surrounding background. The application of high-resolution satellite imagery for automatic detection of tailings dams at large spatial scales has been barely reported. In this study, a target detection method based on deep learning was developed for identifying the locations of tailings ponds and obtaining their geographical distribution from high-resolution satellite imagery automatically. Training samples were produced based on the characteristics of tailings ponds in satellite images. According to the sample characteristics, the Single Shot Multibox Detector (SSD) model was fine-tuned during model training. The results showed that a detection accuracy of 90.2% and a recall rate of 88.7% could be obtained. Based on the optimized SSD model, 2221 tailing ponds were extracted from Gaofen-1 high resolution imagery in the Jing–Jin–Ji region in northern China. In this region, the majority of tailings ponds are located at high altitudes in remote mountainous areas. At the city level, the tailings ponds were found to be located mainly in Chengde, Tangshan, and Zhangjiakou. The results prove that the deep learning method is very effective at detecting complex land-cover features from remote sensing images.

With the development of science and technology, robots have gradually come into our life from industry. Tennis ball collection robot is one of the more prominent representatives. How to find the position of tennis ball accurately is the key. In order to improve the speed and accuracy, we use deep learning and divide the image recognition into two steps. Using AlexNet network model to test whether there is a tennis ball in the picture. If a tennis ball exists, we then use Single Shot multibox Detector (SSD) model to locate the tennis ball, otherwise we use AlexNet to continue to check the next image. Upon verification, we can achieve the desired results.

We propose a lightweight detection algorithm based on the Single Shot MultiBox Detector (SSD) algorithm in order to facilitate sheep management and to realize sheep facial identification, and we take the self-constructed dataset as the research object. First, the SSD replaces the VGG16 backbone network with MobileNetv3, a lightweight neural network, to create a hybrid model that is much smaller. Second, the ECA attention mechanism is incorporated into the backend of the 72 × 160 bottleneck layer. Finally, the SmoothL1 loss function is substituted with the BalancedL1 loss function. The optimized model’s size decreases significantly from the original SSD’s 132 MB to just 22.4 MB. It achieves a mean average precision of 83.47% and maintains an average frame rate of 68.53 frames per second. Compared to the basic SSD model, the mean average precision has increased by 3.25 percentage points, the model size has decreased by 109.6 MB, and the detection speed has improved by 9.55 frames per second. In comparative experiments using the same dataset with different object detection models, the proposed model outperforms the SSD, Faster R-CNN, Retinanet, and CenterNet in terms of mean average precision, with improvements of 3.25 percentage points, 4.71 percentage points, 2.38 percentage points, and 8.13 percentage points, respectively. The detection speed has shown significant improvements, increasing by 9.55, 58.55, 53.1, and 12.37 frames per second, respectively. The improved model presented in this paper significantly reduces the model’s size and computational requirements while maintaining an excellent performance. This provides a valuable reference for the digitalization of animal husbandry and livestock farming.

The vehicle-mounted millimeter-wave radar has been widely used in modern vehicles. The radar needs accurate feedback on the information about the surrounding environment, and the driverless cars also need to have extremely high safety.Therefore, it is of great significance to enhance the ability of the vehicle-mounted millimeter-wave radar to detection of the surrounding targets. Traditional vehicle-mounted millimeter-wave radar usually signals the target echo signal and finally get the target information. In the signal processing process, it is greatly affected by the weather environment, so it is difficult to ensure a sustainable high detection rate. Therefore, a deep learning-based radar spectrum target detection method is proposed to quickly identify the objects present in the echo spectrum. First, the vehiclemounted millimeter radar spectrum mat format data is extracted, make the dataset for training, then adjust and optimize the SSD (Single Shot Multibox Detector) model according to the situation of the data set, and identify the spectral image using the optimized a training model. In the experiment, 11635 pictures were divided into training set and test set at 9:1, and the average mAP of various targets reached 94.35%, thus detecting the radar echo spectrum based on deep learning and achieving good results. The proposed spectral target detection method can be applied to vehicle-mounted millimeterwave radar.

Pedestrian detection is another significant special application of object detection in autonomous vehicles. In contrast to universal object detection, it has similarities and special traits. Nevertheless, there are some difficulties that influence pedestrian detection performance, namely (i) occlusion and deformation (ii) low-quality and multispectral images consisting primarily of lighting conditions, small-scale detection, and target detection extensively, and (iii) true-false pedestrians. Deep learning (DL) methods are a class of artificial intelligence method that can solve the issues mentioned above of pedestrian detection. This paper initially gives an elaborate description of pedestrian detection, difficulties in pedestrian detection, and latest advancements in solving them using the assistance of DL methods with informative discussions, aiming to provide insights to the readers. (2) A new pedestrian detection algorithm (PDA) of true/false pedestrian is suggested here, in which a new YOLO-3D CNN model is applied to reject true/false pedestrian. The primary purpose is to evaluate the performance of the existing 3D CNN taking into consideration the problem of rejecting true false pedestrians based on images captured using the car's onboard cameras and light detection and ranging (LiDAR) sensors. PDA initially utilizes YOLOv3 to capture the entire image for training detector model capable of real-time forecasting. Next, as a feature extractor, it utilizes the MobileNet-SSD that provides great accuracy as well as good trading uptime. PDA then implements the Faster R-CNN method to detect different parts of the object, over the convolutional layer. Lastly, data augmentation techniques are applied in PDA to augment the data coverage by fully exploiting available training data. Simulation results indicate that the proposed pedestrian detection model and PDA improve the accuracy of real and false pedestrians while maintaining real-time requirements.

In view of the fact that the feature layers of different scales in the traditional single shot multibox detector (SSD) are independent of each other, resulting in poor detection performance for small objects. We propose an improved SSD network for small object detection based on dilated convolution and feature fusion, which is called DFSSD. Specifically, by introducing dilated convolution, we enhance the receptive field of the third-level feature map in the network, which enables the feature map to obtain more global information. At the same time, we designed feature fusion module to fuse low-level feature map with detailed information and high-level feature map with rich semantic information. We adjust the prediction box scale of the DFSSD network prediction layer. Our proposed network obtains 78.9% mAP on PASCAL VOC2007 test at 40 FPS and 74.7% AP on difficult objects in car class of KITTI dataset. The results outperform the original SSD model by 1.4 and 1.2 points respectively.

The lack of human initiative to manage their own wastes is one of many reasons why waste management in residential area is not optimal. A system to detect waste type in real time is a necessity to support the waste management process to be faster and optimal. This research propose the waste type detection systems using 2 types of Single Shot Multibox Detector models, SSD300 and SSD512. Both models were compared based on the accuracy and speed of detection on TACO dataset dan Waste Classification Data. SSD512 achieves a better accuracy of 0.63 mAP compared to the accuracy of SSD300, which is 0.57 mAP. Both models can also be said to be real time, with the SSD300's detection speed being faster at 51 fps compared to the SSD512's detection speed at 28 fps.

This paper proposes a pedestrian detection algorithm to which ROI was applied to implement pedestrian detection that is suitable for the embedded environment. Pedestrian detection has computations for unnecessary areas because the entire input images are computed to find pedestrians in the given images. In this paper, a pedestrian detection algorithm that is ideal for the embedded environment is proposed which reduced computations for unnecessary areas by applying ROI. The CENTIRST descriptor method was used for the pedestrian detection algorithm, which was implemented using 512×360 pixel images on an ALDEBARAN board. The proposed pedestrian detection with ROI showed a 16% improved performance of 3.6 frames per second compared to the conventional method.

Small bowel polyps exhibit variations related to color, shape, morphology, texture, and size, as well as to the presence of artifacts, irregular polyp borders, and the low illumination condition inside the gastrointestinal GI tract. Recently, researchers developed many highly accurate polyp detection models based on one-stage or two-stage object detector algorithms for wireless capsule endoscopy (WCE) and colonoscopy images. However, their implementation requires a high computational power and memory resources, thus sacrificing speed for an improvement in precision. Although the single-shot multibox detector (SSD) proves its effectiveness in many medical imaging applications, its weak detection ability for small polyp regions persists due to the lack of information complementary between features of low- and high-level layers. The aim is to consecutively reuse feature maps between layers of the original SSD network. In this paper, we propose an innovative SSD model based on a redesigned version of a dense convolutional network (DenseNet) which emphasizes multiscale pyramidal feature maps interdependence called DC-SSDNet (densely connected single-shot multibox detector). The original backbone network VGG-16 of the SSD is replaced with a modified version of DenseNet. The DenseNet-46 front stem is improved to extract highly typical characteristics and contextual information, which improves the model’s feature extraction ability. The DC-SSDNet architecture compresses unnecessary convolution layers of each dense block to reduce the CNN model complexity. Experimental results showed a remarkable improvement in the proposed DC-SSDNet to detect small polyp regions achieving an mAP of 93.96%, F1-score of 90.7%, and requiring less computational time.

The ability to detect small targets and the speed of the target detector are very important for the application of remote sensing image detection, and in this paper, we propose an effective and efficient method (named CISPNet) with high detection accuracy and compact architecture. In particular, according to the characteristics of the data, we apply a context information scene perception (CISP) module to obtain the contextual information for targets of different scales and use k-means clustering to set the aspect ratios and size of the default boxes. The proposed method inherits the network structure of Single Shot MultiBox Detector (SSD) and introduces the CISP module into it. We create a dataset in the Pascal Visual Object Classes (VOC) format, annotated with the three types of detection targets, aircraft, ship, and oiltanker. Experimental results on our remote sensing image dataset as well as the Northwestern Polytechnical University very-high-resolution (NWPU VRH-10) dataset demonstrate that the proposed CISPNet performs much better than the original SSD and other detectors especially for small objects. Specifically, our network can achieve 80.34% mean average precision (mAP) at the speed of 50.7 frames per second (FPS) with the input size 300 × 300 pixels on the remote sensing image dataset. On extended experiments, the performance of CISPNet in fuzzy target detection in remote sensing image is better than that of SSD.

Single shot multibox detector (SSD) is a state-of-the-art network for real-time object detection. It is originally designed for general datasets. While, for specific datasets, their distribution of ground truth boxes is somehow different and thus, SSD shows unsatisfying performance. In this paper, we improve the performance of SSD on specific datasets. We first dissect the mechanism of predictors, the predicting parameters of a potential detection, in two aspects: classification and localization. Then we reveal the relationship between default boxes and predictors. With this point we finally make an improvement on default box setting and achieve a higher mAP over the original SSD on specific datasets.

Every two months, the Taiwan Power Company will dispatch staffs to each household to read numbers in electricity meters to calculate and collect electricity bills. However, these electricity meter staff sometimes read the wrong meter numbers and so calculate the wrong electricity bill. A system that automatically detects the digital region in electricity meter, could reduce this misreading of numbers and calculate the electricity bill correctly, thereby increasing work efficiency. Herein, the deep learning model SSD (Single Shot MultiBox Detector) is applied and fine-turned to detect the digital region in electricity meter to help the Taiwan Power Company staff. From the experimental results, it is demonstrated that the presented deep learning methods detect the digital region better than the pre-trained SSD model. In the testing experiments, the accuracies of the digital region detection are 100% for both our collected data's and fine-tuned SSD, respectively.