Image Recognition System for Mechanical Parts Based on SSD and YOLOv5

Peas, as a globally significant legume crop, play a crucial role in food production and human nutrition. However, field pests and diseases, drought, high temperature and nutrient deficiency and other stresses seriously affect the yield and quality of peas. Timely and efficient stress monitoring is of great significance for ensuring pea production. This study reviews the advantages of unmanned aerial vehicle (UAV) remote sensing platforms in farmland stress monitoring, including high-throughput phenotypic acquisition and the roles of multispectral, RGB, and thermal infrared sensors. It also analyzes the applicability of commonly used deep learning models (CNN, RNN, Transformer) in crop stress detection. And the application progress of image classification, object detection, and semantic segmentation technologies in identifying crop stress types, a technical framework combining unmanned aerial vehicles and deep learning was constructed. The data collection and annotation process, data preprocessing and enhancement methods, as well as the pipeline for fusing multi-source images with deep learning models were expounded. The identification, degree classification and spatial distribution visualization of physiological stress (drought, nutrient deficiency, high temperature) and biological stress (diseases, pests) were mainly discussed. In the case of field stress detection of peas, the recognition performance of the deep learning model and its application value in field management decisions were verified. The combination of unmanned aerial vehicle (UAV) remote sensing and deep learning technology can achieve precise detection of field stress in peas. This study aims to provide strong support for precision agricultural management.

One of the researcher's interests and challenges is animal identification techniques. There are several challenges that researchers in this field confront that limit detection effectiveness and efficiency, such as picture illumination variation, animal occlusion, colour similarity of animal colours with backdrop environment, and so on. The purpose of this study is to detect and classify multi-label images of mammals, which we propose to do using the Single Shot Multi-Box Detector (SSD) and the MobileNet v1 coco_2017 model. Another objective is to locate and identify several items (animals) from the Mammal category in digital photos. Based on deep learning technology, the recommended SSD is regarded as a more accurate, rapid, and efficient technique to recognise objects of various sizes. We utilised 2000 pictures in the network taken from standard datasets (such as Caltech 101) and the net in this proposal. The SSD framework enhances Convolution Neural Network (CNN) detection and identification operations. During the prediction phase, the network assigns scores to the existence of each object class and draws a box around each object in the picture. Each box includes a name that defines the kind of object, and the score denotes the likelihood of the object's association to that category. During the procedure, boxes are changed to get the best fit to the form of the item. The experimental findings of this work demonstrated the efficacy of identifying and detecting animals even when light, position, and occlusion were varied. The detection and classification accuracy can reach 98.7%. Unlike other comparable efforts, this recommendation is more dependable and accurate, and it identifies a wide variety of Mammals species. Keywords— MobileNet , Convolution Neural Network (CNN), Single Shot Multi-Box Detector (SSD)

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.

Image target detection and recognition is an important research area in image understanding and computer vision, and has attracted extensive attention of scholars for its wide application. In recent years, with the enlightenment of human vision system, deep learning technology has been put forward, and has become a hot spot. The deep learning model has a multi-layer network structure, which can overcome the shortcomings of the traditional image target recognition methods. In the detection and recognition of image targets, deep learning methods are more and more widely used. This is because the deep learning multilayer network structure can express complex functions in a more concise way than the shallow network, and can learn the deep feature representation. Therefore, this paper uses the method based on deep learning, researches on image target detection and recognition, mainly introduces the region proposal based on the depth of learning based target recognition method of support vector machine algorithm and target detection depth. In this paper, deep learning is applied to image detection and recognition, further to improve the accuracy of image detection and recognition. It has important guiding significance in deep learning and image research.

One of the key tasks for a robot operating in uneven terrain, such as in disaster areas, is the search and retrieval of a target object. It is advantageous for the robot to perform these tasks autonomously. With the aim of achieving autonomous object search and retrieval for a tracked mobile robot, this study investigates an object search motion that incorporates object detection and retrieval for a spray can, which serves as the target object, using a quadruped tracked mobile robot developed by the authors. In the object search, the robot utilizes a vision camera to detect the target object. A deep learning model, the Single Shot Multibox Detector (SSD), is employed for object detection, as it is one of the widely used algorithms in deep learning for object localization. Additionally, an image cropping method and a tiling-based approach are applied to effectively detect objects located at longer distances. After the initial search for the object, the robot continuously detects the object through image extraction during its movement toward the target object. For the object retrieval motion, the position and orientation of the object are determined using the robot’s depth camera, based on edge detection. This information allows the robot to calculate the optimal grasping positions for both hands, which are mounted at the end of the front legs. The robot then repositions itself accordingly, aligns its hands with the calculated grasping positions, and executes the grasping motion to securely lift the object, using the front legs as manipulators. Using these methods, we conducted experiments with the robot to evaluate object search and retrieval in outdoor environments. The results demonstrated the robot’s ability to detect the target object at a long distance, move toward the object while maintaining detection, approach it, identify the optimal grasping position, and lift it. Experimental results confirmed the successful execution of these sequential motions for object search and retrieval.

Image noise is a prevalent issue often created by inadequate lighting, cameras of low quality, compression of images and other factors. While low image quality is anticipated to degrade visual identification outcomes, most present object recognition techniques and benchmarks, such as Pascal Visual Object Classes Challenge and Microsoft Common Objects in Context Challenge, concentrate on images of comparatively high quality. Meanwhile, the identification of objects in noisy images in surveillance and other fields is a prevalent issue. In this paper we discuss the detection of objects in noisy images and suggest a new low-cost technique to detect image objects from noisy images. Receiving the benefits of the Single Shot MultiBox Detector (SSD), we have presented an extensive experimental assessment with conventional detectors retrained on noisy images. Results are provided for the prevalent benchmark for object detection Pascal Visual Object Classes. Comparing with other image detection approaches, our technique has provided satisfactory performance at the time of detecting image objects from noisy images. The method can be very effective to the autonomous industries to resolve the object detection related difficulties created by insufficient lighting and lower regulation pictures.

Small object detection is a challenging computer vision problem due to their low feature representation in the images and factors such as occlusions and noise. In images captured from a camera mounted on an unmanned aerial vehicle (UAV), objects are usually acquired in small sizes depending on the UAV flight altitude. The state-of-the-art object detectors often have lower detection accuracy with small objects. New approaches of combining features at multi-levels in the network helps in improving the object detection performance. In this paper, we propose a multi-scale approach of low-level feature combinations with deconvolutional modules on a single shot multibox detection (SSD) object detector to improve the small object detection in images acquired from a UAV. The proposed SSD based architecture is evaluated on UAV datasets to compare its performance with the state-of-the-art detectors.

The efficient separation of coal and gangue in the mining process is of great significance for improving coal mining efficiency and reducing environmental pollution. Automatic detection of coal and gangue is the key and foundation for the separation of coal and gangue. In this paper, we proposed a hierarchical framework for coal and gangue detection based on deep learning models. In this framework, the Gaussian pyramid principle is first used to construct multi-level training data, leading to the sets of coal and gangue image features with multiple scales. Then, the coal and gangue regional proposal networks (CG-RPN) are designed to determine the candidate regions of the target objects in the image. Next, convolution neural networks (CNNs) are constructed to recognize coal and gangue objects on the basis of extracted candidate regions. We performed our method on three different datasets. Experimental results showed that the proposed method improves the detection accuracy of coal and gangue objects by 0.8% compared with the previous methods, reaching up to 98.33%. In addition, our proposed method enables the detection of multiple coal and gangue objects in an individual image and solves the problem of queuing requirements in traditional methods.

As a typical data-driven method, deep learning relies on the availability of a huge amount of labeled data. Due to the serious lack of available samples, especially remote sensing images containing target information, the application of deep learning methods on object detection in remote sensing images is limited. Different from the common approach that tuning the deep learning model parameters to improve the detection performance, in this paper, we propose a simulation samples generating method for training the deep neural network, which can promote object detection ability for arbitrary deep learning framework. Based on the 3D model of target recovered by shape from laser scan technique and remote sensing background images, some image synthesis algorithms are employed for synthesizing multiple view 2D target images, which extends the number of images used in the training stage of a 2D object detection system. Recognition experimental results, using the detection framework of single shot multibox detector (SSD), demonstrate that Poisson image editing and Gaussian blur rendering can improve the quality of simulation remote sensing images, which significantly increases the detection performance of SSD on the various public remote sensing datasets.

Deep learning techniques have recently demonstrated remarkable success in numerous domains. Typically, the success of these deep learning models is measured in terms of performance metrics such as accuracy and mean average precision (mAP). Generally, a model's high performance is highly valued, but it frequently comes at the expense of substantial energy costs and carbon footprint emissions during the model building step. Massive emission of CO2 has a deleterious impact on life on earth in general and is a serious ethical concern that is largely ignored in deep learning research. In this article, we mainly focus on environmental costs and the means of mitigating carbon footprints in deep learning models, with a particular focus on models created using knowledge distillation (KD). Deep learning models typically contain a large number of parameters, resulting in a 'heavy' model. A heavy model scores high on performance metrics but is incompatible with mobile and edge computing devices. Model compression techniques such as knowledge distillation enable the creation of lightweight, deployable models for these low-resource devices. KD generates lighter models and typically performs with slightly less accuracy than the heavier teacher model (model accuracy by the teacher model on CIFAR 10, CIFAR 100, and TinyImageNet is 95.04%, 76.03%, and 63.39%; model accuracy by KD is 91.78%, 69.7%, and 60.49%). Although the distillation process makes models deployable on low-resource devices, they were found to consume an exorbitant amount of energy and have a substantial carbon footprint (15.8, 17.9, and 13.5 times more carbon compared to the corresponding teacher model). The enormous environmental cost is primarily attributable to the tuning of the hyperparameter, Temperature (τ). In this article, we propose measuring the environmental costs of deep learning work (in terms of GFLOPS in millions, energy consumption in kWh, and CO2 equivalent in grams). In order to create lightweight models with low environmental costs, we propose a straightforward yet effective method for selecting a hyperparameter (τ) using a stochastic approach for each training batch fed into the models. We applied knowledge distillation (including its data-free variant) to problems involving image classification and object detection. To evaluate the robustness of our method, we ran experiments on various datasets (CIFAR 10, CIFAR 100, Tiny ImageNet, and PASCAL VOC) and models (ResNet18, MobileNetV2, Wrn-40-2). Our novel approach reduces the environmental costs by a large margin by eliminating the requirement of expensive hyperparameter tuning without sacrificing performance. Empirical results on the CIFAR 10 dataset show that the stochastic technique achieves an accuracy of 91.67%, whereas tuning achieves an accuracy of 91.78%-however, the stochastic approach reduces the energy consumption and CO2 equivalent each by a factor of 19. Similar results have been obtained with CIFAR 100 and TinyImageNet dataset. This pattern is also observed in object detection classification on the PASCAL VOC dataset, where the tuning technique performs similarly to the stochastic technique, with a difference of 0.03% mAP favoring the stochastic technique while reducing the energy consumptions and CO2 emission each by a factor of 18.5.

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.

In the metallurgical industry, online monitoring of belt conveyors' mineral raw material flow intensity helps avert severe accidents during production. There is no established method for detecting mineral raw material flow intensity in real time using computer-based technologies. So, we proposed two computer vision processing methods: traditional image processing algorithm approach and a CNN (Convolutional Neural Networks) MobileNetV2-SSD (Single Shot MultiBox Detector) detection method based on deep learning. We created a dataset containing 5731 images and experimented it on both methods, and also assessed it on different convolutional neural network models. In summary, the conventional image processing algorithm holds an accuracy of 81.68%, whereas the MobileNetV2- SSD model exhibited 99.65% accuracy. The MobileNetV2-SSD reflected significant advantages over other models in terms of accuracy and time consumption. So, we conclude that MobileNetV2-SSD mineral raw material flow intensity detection model can be widely used in metallurgical production to automate the production process and improve productivity.

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.

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.

In the modern era, object detection and analysis is one of the crucial tasks. Numerous challenges have to be faced by the researchers to analyze the objects in images and real-time videos. Such analysis is required in multiple domains such as monitoring health, self-driving including detection of an anomaly, and many more. With the advanced usage of deep learning (DL) models and GPUs, the efficacy of object detection has been improved very well. Therefore, in this paper, we have provided a detailed study of both cases (images and videos) to detect specific objects using DL models. The existing approaches have been compared using on global wheat-head detection dataset to check the performance for object detection and recognition at different stages. From this analysis, we can say that DL is a backbone of computer vision to detect and recognize the various objects in a real-time scenario.KeywordsObject detectionGPUDeep learningYOLO