Image Recommendation for Automatic Report Generation using Semantic Similarity

Retail product recognition on grocery shelf photographs is a challenging task due to the variety of products and lighting conditions. This research proposes a novel method for completing this task efficiently and in a short amount of time. The object detection and recognition module is deployed on a jetson Nano board, which is trained to trace a path for real time object image capture. The proposed method consists of two stages: detection and recognition. The detection stage is performed by a generic product detection module that has been trained on a particular class of products (e.g., tobacco packages). This is accomplished using the Viola and Jones Cascade Object Detection Framework. The recognition stage is performed using two FCN designs: U-Net and Fully Convolutional Regression Network (FCRN). We extract both shape and color information by applying feature-level fusion to two distinct descriptors computed using the bag of words method. We evaluated our method on a dataset of grocery shelf photographs. We achieved a detection accuracy of 95% and a recognition accuracy of 90%. The proposed method is efficient and accurate, and it can be used for a variety of applications, such as inventory management, price tracking, and fraud detection.

The objects in remote sensing images usually have complex background and appear anywhere in any direction, which poses challenges for deep learning-based object detection. In order to solve the above problems, we embed the local binary pattern (LBP) into deep learning-based object detection to facilitate performance improvements. Specifically, we implement thep LBP via depthwise separable convolution without any learnable parameters, which makes LBP highlight the object-related regions of feature map instead of original images. The convolutional implementation of LBP makes it easy to embed it in deep learning-based object detection, so that deep learning-based object detection can possess the ability of LBP to extract the texture information from complex background without having to learn. The gradients of the branch where LBP convolution is located are blocked and cannot be backpropagated according to proposed LBP convolution, so we propose an effective residual block, called LBPRes (Residual block with Local Binary Pattern) for normal training. To deal with the problem of object direction changes, we introduce the rotation invariance into the LBPRes, denoted as RILBPRes (LBPRes with Rotation Invariance), which makes deep learning-based object detection have the local rotation invariance to cope with the object direction changes. Finally, we construct a single-stage object detection network S2LBPNet (Single Stage object detection Network with Local Binary Pattern) with a local binary pattern and conduct related experiments on the DIOR and HRRSD datasets. According to the experimental results, with a small number of parameters added, S2LBPNet outperforms the YOLOv5s baseline by 2.2% and 5.1% on DIOR and HRRSD datasets, respectively, which prove the superiority of the proposed S2LBPNet.

Existing night vehicle detection methods mainly detect vehicles by detecting headlights or taillights. However, these features are adversely affected by the complex road lighting environment. In this paper, a cascade detection network framework FteGanOd is proposed with a feature translate-enhancement (FTE) module and the object detection (OD) module. First, the FTE module is built based on CycleGAN and multi-scale feature fusion is proposed to enhance the detection of vehicle features at night. The features of night and day are combined by fusing different convolutional layers to produce enhanced feature (EF) maps. Second, the OD module, based on the existing object detection network, is improved by cascading with the FTE module to detect vehicles on the EF maps. The proposed FteGanOd method recognizes vehicles at night with greater accuracy by improving the contrast between vehicles and the background and by suppressing interference from ambient light. The proposed FteGanOd is validated on the Berkeley Deep Drive (BDD) dataset and our private dataset. The experimental results show that our proposed method can effectively enhance vehicle features and improve the accuracy of vehicle detection at night.

Object detection is increasingly in demand in IoT service applications. Deep learning based object detection algorithms are now in fashion. As the most popular multi-scale object detection network at present, Feature Pyramid Network achieves feature augmentation by fusing features of neighboring layers. It is widely used in the most advanced object detectors to detect objects of different scales. In this paper, we propose a new attention mechanism guided bidirectional feature pyramid architecture named AgBFPN to enhance the transfer of semantic and spatial information between each feature map. We design Channel Attention Guided Fusion(CAGF) Module and Spatial Attention Guided Fusion(SAGF) Module to enhance feature fusion. The CAGF mitigates the loss of information induced by channel reduction and better transfers the semantic information from high-level to low-level features. The SAGF passes the rich spatial information of shallow features into deep features. Our experiments show that AgBFPN achieves higher Average Precision for multi-scale object detection.

In this paper, a scene perception and recognition module aimed at use in typical industrial scenarios is presented. The major contribution of this work lies in a 3D object detection, recognition and pose estimation module, which can be trained using CAD models and works for noisy data, partial views and in cluttered scenes. This algorithm was qualitatively and quantitatively compared with other state-of-art algorithms. Scene perception and recognition is an important aspect in the design of intelligent robotic systems which can adapt to unstructured and rapidly changing environments. This work has been used and evaluated in several experiments and demonstration scenarios for autonomous process plan execution, human-robot interaction and co-operation.

In recent years, computer vision technology has developed rapidly, as one of its important research directions, object detection has received widespread attention due to its high accuracy. Meanwhile, object detection has many application fields, such as intelligent transportation, medical and health, security systems, etc. Traditional object detection methods have limitations when applied to complex real-world scenarios. To improve the shortcomings of conventional methods, deep learning based object detection algorithms have significantly improved the efficiency of object detection and become a research hotspot in object detection. This article summarizes the algorithms into two-stage and one-stage object detection algorithms based on the technical processes and structural differences in handling object detection tasks. Firstly, several common two-stage and one-stage object detection algorithms and their applications in real-world scenarios are introduced. Then their data sets and algorithm performance are analyzed and compared. Finally, according to the results of the comparison, the existing problems of the two-stage object detection algorithm and the one-stage object detection method are discussed, and their future development directions are pointed out.

Deep learning-based object detection in low-altitude UAV datasets: A survey

As one of the hottest fields of computer vision, object detection is employed in many useful applications, including face recognition, autonomous cars and human behaviour analysis. CNN's have played a vital role in the progression of computer vision, especially object detection. In this paper, a review is provided on object detection methods which utilize deep learning to render outstanding results, and different object detection frameworks are discussed and analyzed with respect to their differences amongst each other. The comparisons are carried out based upon the criterion of accuracy and frames per second. The review starts with the explanation of CNNs and their advantages. Then we focus our attention on two types of object detection architectures and dive deep into their respective details. In the end, we draw a conclusion based on the facts detailed in the review.

Convolutional neural network based methods have dominated object detection in recent years, which can be divided into the one-stage approach and the two-stage approach. In general, the two-stage approach (e.g., Faster R-CNN) achieves high accuracy, while the one-stage approach (e.g., SSD) has the advantage of high efficiency. To inherit the merits of both while overcoming their disadvantages, we propose a novel single-shot based detector, namely RefineDet++, which achieves better accuracy than two-stage methods and maintains comparable efficiency of one-stage methods. The proposed RefineDet++ consists of two inter-connected modules: the anchor refinement module and the alignment detection module. Specifically, the former module aims to (1) filter out negative anchors to reduce search space for the subsequent classifier, and (2) coarsely adjust the locations and sizes of anchors to provide better initialization for the subsequent regressor. The latter module takes (1) the refined anchors as the input from the former module with (2) a newly designed alignment convolution operation to further improve the regression accuracy and predict multi-class label. Meanwhile, we design a transfer connection block to transfer the features in the anchor refinement module to predict locations, sizes and class labels of objects in the object detection module. The multi-task loss function enables us to train the whole network in an end-to-end way. Extensive experiments on PASCAL VOC and MS COCO demonstrate that RefineDet++ achieves state-of-the-art detection accuracy with high efficiency.

Object detection based on deep learning has become one of the most widely used and popular research topics in the field of computer vision. This paper firstly reviews the development of target detection technology and analyzes and summarizes the advantages and disadvantages of traditional target detection methods. Then, several target detection technologies based on deep learning and their advantages and disadvantages are introduced in detail. Finally, the possible future development of object detection is discussed.

Despite significant advances in deep learning based object detection in recent years, training effective detectors in a small data regime remains an open challenge. This is very important since labelling training data for object detection is often very expensive and time-consuming. In this paper, we investigate the problem of few-shot object detection, where a detector has access to only limited amounts of annotated data. Based on the meta-learning principle, we propose a new meta-learning framework for object detection named which learns the ability to perform few-shot detection via meta-learning. Specifically, Meta-RCNN learns an object detector in an episodic learning paradigm on the (meta) training data. This learning scheme helps acquire a prior which enables Meta-RCNN to do few-shot detection on novel tasks. Built on top of the popular Faster RCNN detector, in Meta-RCNN, both the Region Proposal Network (RPN) and the object classification branch are meta-learned. The meta-trained RPN learns to provide class-specific proposals, while the object classifier learns to do few-shot classification. The novel loss objectives and learning strategy of Meta-RCNN can be trained in an end-to-end manner. We demonstrate the effectiveness of Meta-RCNN in few-shot detection on three datasets (Pascal-VOC, ImageNet-LOC and MSCOCO) with promising results.

To alleviate the costly data annotation problem in deep learning-based object detection, we leverage the canonical view model for active sample selection to improve the effectiveness of learning. Inspired by the view-approximation model, we hypothesize that visual features learned from canonical views denote better representations of objects, thus boosting the effectiveness of object learning. We validate the hypothesis empirically in the context of robot learning for novel object detection. Based on this, we propose a novel on-line viewpoint exploration (OLIVE) method that (1) defines goodness-of-view by combining informativeness of visual features and consistency of model-based object detection, and (2) systematically explores and selects viewpoints to boost learning efficiency. Furthermore, we train a legacy Faster R-CNN model with a data augmentation method while leveraging data samples generated by the OLIVE pipeline. We test our method on the T-LESS dataset and show that the proposed method outperforms competitive benchmarking methods, especially when the samples are few.

Objective To develop and evaluate an automated system for digitizing audiograms, classifying hearing loss levels, and comparing their performance with traditional methods and otolaryngologists' interpretations.Designed and Methods We conducted a retrospective diagnostic study using 1,959 audiogram images from patients aged 7 years and older at the Faculty of Medicine, Vajira Hospital, Navamindradhiraj University. We employed an object detection approach to digitize audiograms and developed multiple machine learning models to classify six hearing loss levels. The dataset was split into 70% training (1,407 images) and 30% testing (352 images) sets. We compared our model's performance with classifications based on manually extracted audiogram values and otolaryngologists' interpretations.Result Our object detection-based model achieved an F1-score of 94.72% in classifying hearing loss levels, comparable to the 96.43% F1-score obtained using manually extracted values. The Light Gradient Boosting Machine (LGBM) model is used as the classifier for the manually extracted data, which achieved top performance with 94.72% accuracy, 94.72% f1-score, 94.72 recall, and 94.72 precision. In object detection based model, The Random Forest Classifier (RFC) model showed the highest 96.43% accuracy in predicting hearing loss level, with a F1-score of 96.43%, recall of 96.43%, and precision of 96.45%.Conclusion Our proposed automated approach for audiogram digitization and hearing loss classification performs comparably to traditional methods and otolaryngologists' interpretations. This system can potentially assist otolaryngologists in providing more timely and effective treatment by quickly and accurately classifying hearing loss.

Recognizing objects and estimating their poses have a wide range of application in robotics. For instance, to grasp objects, robots need the position and orientation of objects in 3D. The task becomes challenging in a cluttered environment with different types of objects. A popular approach to tackle this problem is to utilize a deep neural network for object recognition. However, deep learning-based object detection in cluttered environments requires a substantial amount of data. Collection of these data requires time and extensive human labor for manual labeling. In this study, our objective was the development and validation of a deep object recognition framework using a synthetic depth image dataset. We synthetically generated a depth image dataset of 22 objects randomly placed in a 0.5 m × 0.5 m × 0.1 m box, and automatically labeled all objects with an occlusion rate below 70%. Faster Region Convolutional Neural Network (R-CNN) architecture was adopted for training using a dataset of 800,000 synthetic depth images, and its performance was tested on a real-world depth image dataset consisting of 2000 samples. Deep object recognizer has 40.96% detection accuracy on the real depth images and 93.5% on the synthetic depth images. Training the deep learning model with noise-added synthetic images improves the recognition accuracy for real images to 46.3%. The object detection framework can be trained on synthetically generated depth data, and then employed for object recognition on the real depth data in a cluttered environment. Synthetic depth data-based deep object detection has the potential to substantially decrease the time and human effort required for the extensive data collection and labeling.

Lightweight object detection and recognition models are extremely crucial for in-orbit applications, which is the most critical factor for whether deep learning-based object detection and recognition algorithms can be applied to remote sensing satellites for real-time or near real-time processing. Global information is extremely important for object detection and recognition of remote sensing images. However, due to the high computational cost, the existing CNN-based lightweight models over-emphasize on the extraction of local information, while ignoring the global information. For this reason, we propose a lightweight object detection and recognition model (Lightweight Global-Local Detection, LGLDet) based on the especially light global modeling structure. In LGLDet, light global-local module (LGLM) is proposed to extract the global and local information. The LGLM consists of Point2Patch Non-Local (P2PNL), local branch and skip connection. Specifically, P2PNL is proposed to reduce the computation of global long-range dependency modeling. In addition, the feature fusion part and detection head are also designed in a lightweight way. In the experiments, the proposed method can achieve optimal performance with fewer parameters and lower computational complexity than existing CNN-based lightweight models and transformer-based lightweight models with similar parameters or computational complexity. The code will be released on the site of https://github.com/dyl96/LGLDet.