Single Shot Multibox Detector Automatic Polyp Detection Network Based on Gastrointestinal Endoscopic Images.

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.

Over the last few years, researchers have focused on computer‐aided polyp detection in gastroscopy. Deep learning (DL) has shown great promise for polyps' identification. The most exceptional contribution of DL methods in gastroenterology is their ability to identify polyps quickly and accurately using convolution neural network. Nonetheless, despite significant advancements, automatic detection of small polyps remains a challenging and complex task. Furthermore, due to multiple pooling operations, the features of small polyps are lost, resulting in low detection accuracy. This paper proposes an efficient object detection method for polyp detection using gastric images to address this issue. A single‐shot multi‐box detector (SSD) was combined with the feature extractor VGG‐16, and the Refined Map Block (RMB) was integrated into SSD's high‐resolution feature maps to get more semantic information. The RMB output was used as the input to the successive layers. The RMB comprises of attention cascade and feature map concatenation cascade. The attention cascade improved the localization accuracy, while the feature map concatenation cascade improved the classification accuracy. Using the former, the proposed attention‐based SSD for gastric polyps (ASSD‐GPNet) model focused on the specific information, a polyp, rather than the background. Furthermore, the feature map concatenation cascade adds semantic information while reducing computational complexity. The output of these two cascades was combined to produce a refined feature map that enhances the detection of small polyps. The model was trained and tested on 1970 gastric images and Pascal VOC07 + 12. Image augmentation was applied to increase the training data of gastric images to reduce overfitting and skip connections were used to overcome the vanishing gradient problem. Overall, the experimental results demonstrated that the proposed model outperformed than compared models in both medical and natural images. The ASSD‐GPNet obtained mean average precision (mAP) of 94.2% on gastric images and 76.9% on Pascal VOC.

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.

Lightweight target detection for the field flat jujube based on improved YOLOv5

Abstract: This research addresses the crucial task of real-time vehicle detection and traffic analysis on highways and busy roads, employing advanced object detection algorithms & deep learning techniques. The study focuses on identifying various vehicle types, including cars, SUVs, bikes, buses, and trucks, using four distinct algorithms: Single Shot Multibox Detector (SSD), Kalman Filter Algorithm, You Only Look Once (YOLO v7), and Mask Regional-Convolutional Neural Network (Mask R-CNN). The main goal of the research is to apply these algorithms in real-world settings on busy metropolitan roads and highways for purpose of traffic analysis. The study software is designed to monitor traffic flow and count the number of cars that pass by in a given period of time, like a day, a week, or a month. Additionally, the algorithm sorts these cars into various categories and offers a thorough statistical breakdown of the normal vehicle composition on the road under observation. The research's conclusions help politicians, transportation engineers, and urban planners by providing insightful information about traffic patterns. These algorithms enable data- driven analysis, which in turn informs decisions on traffic management, road infrastructure, and safety protocols. Through the integration of state-of-the-art technology with practical applications, this research makes a substantial contribution to the improvement of traffic monitoring systems, thereby facilitating safer and more intelligent urban movemen

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.

Nursery plays an important role on starting chili cultivation, determining the crop health, fertility from disease, and growth performance. Early-stage germination detection is necessary to minimize nursery failure and improve plant health, but manual detection is challenging for large scale nursery in the greenhouse. The aim of this research was to develop an automatic detection model integrated with a You Only Look Once (YOLO) based deep learning algorithm using RGB camera to monitor the chili germination stages. Method to detect germination was YOLO with several steps, included: (1) early stages chili germination images acquisition, (2) datasets preparations, (3) dataset annotation and labeling, (4) model development using deep learning YOLO algorithms, and (5) model testing and validation. The training of 11,423 images was conducted utilizing the YOLOv5 and YOLOv8 algorithms, which categorized into, three classes (germinated, not germinated, and cotyledon appearance). The model was evaluated using mean Average Precision (mAP), precision, accuracy, and recall with the respective values of 0.697, 73%, 75%, and 73% for YOLOv8, and 0.664, 70%, 73%, and 70% for YOLOv5. Both model achieved high accuracy, but YOLOv8 was better to detect and classify chili seedling growth stages than YOLOv5. This study also demonstrated that model can be implemented in real applications integrated with automatic monitoring system included in the model. Keywords: Chili seedling, Deep learning, Detection system, Germination.

Simple SummaryIn the process of breeding geese, manually recording data causes the problems of missing and confusing characterization data; furthermore, manual intervention can lead to the stress response of breeding geese and affect the laying efficiency of breeding geese. In this study, we tried to combine the Internet of things and computer image technology to improve the accuracy of data recording, so as to achieve an accurate correspondence between breeding goose individual data and egg-laying data. Therefore, we developed and tested a breeding egg identification and coding system to realize the selection of high-quality breeding geese. The test results showed that the system realized a correspondence of 97.8% between breeding goose individual data and egg-laying data. The system realized the information recording of breeding geese under nonmanual intervention, realized the correspondence between individual data and egg-laying data, and improved the health and welfare of breeding geese.The selection of breeding geese requires the recording of egg production information to correspond to the identity of the breeding geese. However, due to the special physiological characteristics of breeding geese, manual recording in practice can affect the egg-laying performance of breeding geese and can also lead to problems of missing and confusing individual breeding goose data with the number of eggs laid by the geese. For contactless recording of breeding goose identity and egg production information for high-quality breeding, this paper proposes an Internet of things (IoT)-based breeding egg identification and coding method for the selection of high-quality breeding geese. At the sensing level, we deployed a radiofrequency identification (RFID)-based sensor. Each breeding goose wore a foot ring RFID tag on its leg, and the individual information was read by foot ring RFID readers placed at the bottom of the devices. Individual information was uploaded to the cloud server for database management through structured query language (MySQL). The target detection modules were mounted on top of the devices, and the breeding geese and eggs were detected in the delivery rooms by an improved single-shot multi-box detector (SSD) target detection algorithm. The egg body limit transmission device and contactless coding device were activated only in the case of breeding eggs, and the breeding goose information was printed on the egg bodies in the form of quick response codes (QR codes), which enabled the breeding egg information to correspond with the breeding goose information. An evaluative experiment was performed using a system for the selection of high-quality breeding geese, with web cameras and a cloud monitoring platform. The breeding geese were allowed 14 days to become accustomed to the experimental environment before monitoring began. The evaluative experiment results showed that the pass rate of egg body coding reached 98.25%, the improved SSD algorithm was 8.65% more accurate and 62.6 ms faster than traditional SSD, and the accuracy rate corresponding to the individual information of the breeding geese and the surface information of the goose eggs was 97.8%. The experimental results met the requirements of accurate marking of individual information of breeding geese, which can provide technical support for the selection of high-quality breeding geese.

Posture detection targeted towards providing assessments for the monitoring of health and welfare of pigs has been of great interest to researchers from different disciplines. Existing studies applying machine vision techniques are mostly based on methods using three-dimensional imaging systems, or two-dimensional systems with the limitation of monitoring under controlled conditions. Thus, the main goal of this study was to determine whether a two-dimensional imaging system, along with deep learning approaches, could be utilized to detect the standing and lying (belly and side) postures of pigs under commercial farm conditions. Three deep learning-based detector methods, including faster regions with convolutional neural network features (Faster R-CNN), single shot multibox detector (SSD) and region-based fully convolutional network (R-FCN), combined with Inception V2, Residual Network (ResNet) and Inception ResNet V2 feature extractions of RGB images were proposed. Data from different commercial farms were used for training and validation of the proposed models. The experimental results demonstrated that the R-FCN ResNet101 method was able to detect lying and standing postures with higher average precision (AP) of 0.93, 0.95 and 0.92 for standing, lying on side and lying on belly postures, respectively and mean average precision (mAP) of more than 0.93.

Fish kills are sudden mass mortalities that occur in freshwater and marine systems worldwide. Fish kill surveys are essential for assessing the ecological and economic impacts of fish kill events, but are often labor-intensive, time-consuming, and spatially limited. This study aims to address these challenges by exploring the application of unoccupied aerial systems (or drones) and deep learning techniques for coastal fish carcass detection. Seven flights were conducted using a DJI Phantom 4 RGB quadcopter to monitor three sites with different substrates (i.e., sand, rock, shored Sargassum). Orthomosaics generated from drone imagery were useful for detecting carcasses washed ashore, but not floating or submerged carcasses. Single shot multibox detection (SSD) with a ResNet50-based model demonstrated high detection accuracy, with a mean average precision (mAP) of 0.77 and a mean average recall (mAR) of 0.81. The model had slightly higher average precision (AP) when detecting large objects (>42.24 cm long, AP = 0.90) compared to small objects (≤14.08 cm long, AP = 0.77) because smaller objects are harder to recognize and require more contextual reasoning. The results suggest a strong potential future application of these tools for rapid fish kill response and automatic enumeration and characterization of fish carcasses.

This paper describes the use of two different deep-learning algorithms for object detection to recognize different badgers. We use recordings of four different badgers under varying background illuminations. In total four different object detection algorithms based on deep neural networks are compared: The single shot multi-box detector (SSD) with the Inception-V2 or MobileNet as a backbone, and the faster region-based convolutional neural network (Faster R-CNN) combined with Inception-V2 or residual networks. Furthermore, two different activation functions are compared to compute probabilities that some badger is in the detected region: the softmax and sigmoid functions. The results of all eight models show that SSD obtains higher recognition accuracies (97.8%–98.6%) than Faster R-CNN (84.8%–91.7%). However, the training time of Faster R-CNN is much shorter than that of SSD. The use of different output activation functions seems not to matter much.

This work presents an automated system for recognizing Brazilian vertical traffic signs and lights using artificial intelligence. The main objective of the system is to contribute to road safety by alerting drivers to potential risks such as speeding, alcohol consumption, and cell phone use, which could lead to severe accidents. The system’s core contribution lies in its ability to accurately recognize various traffic signs and lights, providing crucial warnings to drivers. To achieve this, the system utilizes a light version of the single shot multi box detector as its detection algorithm and experiments with three Mobilenet versions as base networks. The optimal Mobilenet version is selected based on a mean average precision higher than 80%, which guarantees reliable detection results. The dataset used for training and evaluation comprises images extracted from YouTube traffic videos, each annotated to create the necessary labels for training. Through this extensive experimentation, the system demonstrates its efficacy in achieving accurate and efficient detection. The results of the experiments are compared with other existing approaches and our work significantly advances the field by providing a tailored dataset, an optimized model, and also valuable insights into traffic sign and light recognition, collectively contributing to the improvement of road safety.

The indoor scene object detection technology is of important research significance, which is one of the popular research topics in the field of scene understanding for indoor robots. In recent years, the solutions based on deep learning have achieved good results in object detection. However, there are still some problems to be further studied in indoor object detection methods, such as lighting problem and occlusion problem caused by the complexity of the indoor environment. Aiming at these problems, an improved object detection method based on deep neural networks is proposed in this article, which uses a framework similar to the single-shot multibox detector (SSD). In the proposed method, an improved ResNet50 network is used to enhance the transmission of information, and the feature expression capability of the feature extraction network is improved. At the same time, a multiscale contextual information extraction (MCIE) module is used to extract the contextual information of the indoor scene, so as to improve the indoor object detection effect. In addition, an improved dual-threshold non-maximum suppression (DT-NMS) algorithm is used to alleviate the occlusion problem in indoor scenes. Finally, the public dataset SUN2012 is further screened for the special application of indoor scene object detection, and the proposed method is tested on this dataset. The experimental results show that the mean average precision (mAP) of the proposed method can reach 54.10%, which is higher than those of the state-of-the-art methods.

Object detection with deep learning model has achieved good results in many fields, but in some fields that think highly of data privacy, such as medical care, its applications is greatly limited by data. And Federated Learning allows clients to train a model together, while leaving their data in the local, without sharing with the server or other clients. Using the methods of Federated Learning, such as Federated Averaging(FedAvg), to train models can provide privacy, security benefits. Nonetheless, there is little experiment applying Federated Learning algorithms to train the model with a large number of parameters, such as deep learning object detection model. With non-IID data, the accuracy of object detection model trained by FedAvg reduces significantly, and need more rounds to coverage. In this work, we use Kullback-Leibler divergence(KLD) measure the weights divergence between different model trained with non-IID data. And we propose a useful scheme to improve FedAvg based Abnormal Weights Supression, reducing the influence of the weights divergence caused by non-IID and unbalanced data. As a representative of object detection, we choose Single Shot MultiBox Detector(SSD) as the base model. The results of the experiments show that the Mean Average Precision(mAP) get obvious improvement in Pascal VOC 2007 test dataset.

Marine life detection based on deep learning has always been the focus and difficulty in the field of deep learning target detection. There are two main problems. First, underwater imaging often has problems such as low image contrast, blurred image, color shift, and blue-green tint of the background. How to solve these problems in imaging. Second, there are many algorithms in the field of deep learning target detection, how to choose a suitable algorithm for marine life detection. Aiming at the above problems, this paper firstly introduces three algorithms suitable for underwater image enhancement: the method based on dark channel prior, the method based on histogram equalization and the method based on Retinex. Then, six commonly used deep learning target detection algorithms are introduced from two aspects: target detection algorithm based on candidate region proposal and target detection algorithm based on regression: R-CNN, Fast R-CNN, Faster R-CNN, Mask R-CNN, YOLO, SSD, and each analyzes their advantages and disadvantages. It provides a theoretical and method reference for deep learning-based marine biological detection.