PointVoxel-Net: A Residual Learning Approach to Human Pose-Oriented 3D Classification Using PointGrid Features

We propose a framework for three-dimensional (3D) object recognition and classification in very low illumination environments using convolutional neural networks (CNNs). 3D images are reconstructed using 3D integral imaging (InIm) with conventional visible spectrum image sensors. After imaging the low light scene using 3D InIm, the 3D reconstructed image has a higher signal-to-noise ratio than a single 2D image, which is a result of 3D InIm being optimal in the maximum likelihood sense for read-noise dominant images. Once 3D reconstruction has been performed, the 3D image is denoised and regions of interest are extracted to detect 3D objects in a scene. The extracted regions are then inputted into a CNN, which was trained under low illumination conditions using 3D InIm reconstructed images, to perform object recognition. To the best of our knowledge, this is the first report of utilizing 3D InIm and convolutional neural networks for 3D training and 3D object classification under very low illumination conditions.

This paper proposes a method for recognition and classification of 3D objects using 2D moments and HMLP network. The 2D moments are calculated based on 2D intensity images taken from multiple cameras that have been arranged using multiple views technique. 2D moments are commonly used for 2D pattern recognition. However, the current study proves that with some adaptation to multiple views technique, 2D moments are sufficient to model 3D objects. In addition, the simplicity of 2D moment's calculation reduces the processing time for feature extraction, thus decreases the recognition time. The 2D moments were then fed into a neural network for classification of the 3D objects. In the current study, hybrid multi-layered perceptron (HMLP) network is proposed to perform the classification. Two distinct groups of objects that are polyhedral and free-form objects were used to access the performance of the proposed method. The recognition results show that the proposed method has successfully classified the 3D object with the accuracy of up to 100%.

The estimation of 3D orientation based on nine-axis inertial measurement unit (IMU) is an essential technology in various applications, from unmanned aerial vehicle to human motion tracking. Various sensor fusion filter algorithms such as Kalman filter (KF) or complementary filter (CF) have been proposed for accurate 3D orientation estimation. However, the degradation of estimation performance due to disturbance components such as magnetic distortion and external acceleration is still a critical issue. An alternative approach for the orientation estimation task is to train a neural network end-to-end with a variety of massive experimental datasets consisting of the raw IMU signals and the ground truth orientations. This paper proposes a recurrent neural network (RNN) for robust IMU-based 3D orientation estimation. Overall, this paper is an extension of the previous work by Weber et al., where the RNN model was used to estimate the quaternion, but only the attitude estimation performance was investigated without considering the heading estimation. The proposed RNN receives a nine-dimensional sensor signal as an input and outputs a unit quaternion representing 3D orientation, and it can robustly estimate the orientation across various motion characteristics and magnetic environments without needing an additional filter algorithm. Verification results showed that the proposed method outperformed the conventional CF and KF algorithms. In particular, in magnetically disturbed conditions, the averaged root mean square error of the proposed RNN approach was reduced by 41.4% and 60.3%, respectively, when compared to the CF and the KF algorithm.

This paper presents a new method for 3D position and orientation estimation based on the magnetic field generated by a single coil and the fusion of low power magnetometers and inertial sensors. The fixed spatial relationship between the sensors is exploited to solve the ambiguity problem that occurs when only a single coil is employed. In this context a new positioning algorithm is developed and verified by simulations. Using a single coil instead of three coils as common in conventional magnetic field based systems brings a benefit both regarding power consumption and construction size. Moreover, as the proposed system requires no line of sight between source and sensors, it is ideally suited for portable, location-independent applications such as the mobile assessment of a persons' head to torso posture and movement e.g. for the purpose of examining causes for chronic pain in the cervical spine area under conditions of daily life.

This paper proposes an effective method for recognition and classification of 3D objects using multiple views technique and neural networks system. In the processing stage, we propose to use 2D moment invariants as the features for modeling 3D objects. 2D moments have been commonly used for 2D object recognition. However, we have proved that with some adaptation to multiple views technique, 2D moments are sufficient to model 3D objects. In addition, the simplicity of 2D moments calculation reduces the processing time for feature extraction, hence increases the system efficiency. In the recognition stage, we propose a cascaded multilayered perceptron (c-MLP) network for matching and classification. The c-MLP contains two MLP networks which are arranged in a serial combination. This proposed method has been tested using two groups of object, polyhedral and free-form objects. We also compare our method with standard MLP network. Our results show that the proposed method can successfully be applied to 3D object recognition. In addition, the proposed network also achieved better performance and faster convergence rate compared to the than standard MLP

Nowadays, point clouds are frequently gathered by 3D scanners such as Lidar and Kinect, which produces thousands of point cloud models. Point cloud processing is vital to 3D vision, especially 3D object recognition, positioning, and navigation technology. Addressing uneven data density caused by coordinate frame transformations and the inherent problem of insufficient context connection in point clouds, the DiM-PCNet (Multi-scale and Multi-level Point Clouds Classification Network, and the Di is a prefix to represent double M in Multi-scale and Multi-level) is proposed in this paper. DiM-PCNet is provided for object classification with multi-scale and multi-level features. We encode the point cloud in multi-scale and fully fuse the features with the raw point cloud for keeping the context relationship. In DiM-PCNet, we sample the point clouds from eight parts for multi-scales feature extraction. The multi-scales features are fully fused by multi-level pyramid models. The multi-scale and multi-level strategies are applied in DiM-PCNet, in which the abundant and important features of point clouds are extracted and utilized in the 3D object classification. It is worth noting that the DiM-PCNet feature block can be embedded into the segmentation net, where the accuracy achieved is 87.1%. We conducted experiments on ShapeNet and ModelNet40 and the experimental results show that DiM-PCNet achieves state-of-the-art performance in 3D object classification. The experiment shows competitive performance on robustness and segmentation tasks.

A cross-entropy method for the classification of 3D objects with curved surfaces is proposed. In the proposed approach, small cross-entropy between the shape histograms of two objects indicates that the two objects are similar, where the shape histogram is defined as the distribution of the shape indices computed at pixels on the object. Experiments with real range images show that the cross-entropy method can be used to classify 3D objects with curved surfaces.

Object pose estimation is an important application in 3D recognition. A 3D object pose estimating method is developed for an automated manufacturing assembly application. The target parts are extracted from the original range images using the traditional edge detection and segmentation methods. The center position is then computed through the circle Hough transform algorithm. For the 3D orientation estimation, a 3D geometrical feature descriptor, Angle Distance Map (ADM), is proposed to describe the 3D local surface feature. A triangular mesh model of 3D object is used for reducing the computational complexity. The principal component analysis (PCA) method is applied on the ADM descriptions for efficient comparison. The orientation information is computed according to the extracted 3D feature points. The proposed method is tested in an application for flexible robot assembly. The experimental results show that accurate 3D pose estimation can be obtained.© (2002) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Abstract: Real-time object detection is essential in areas like surveillance, autonomous vehicles, and smart cities.This project uses YOLOv5, a fast and accurate one-stage deep learning model, for object detection.Transfer learning is applied by fine-tuning pre-trained weights on a custom dataset of 5,000 images.The model includes CSPDarknet53 and PANet to improve feature extraction and multi-scale detection.It effectively detects small, occluded, and multiple objects in complex scenes.Trained over 50 epochs, it achieved high accuracy using precision, recall, and mAP metrics.Deployment was done using OpenCV DNN for real-time CPU-based inference.The system shows strong real-world potential, with future scope in edge and IoT applications. Index Terms: YOLOv5, Real-Time Object Detection, Deep Learning, Transfer Learning, CNN, CSPDarknet53, PANet, Pascal VOC, Bounding Box, Data Augmentation, OpenCV, Edge Deployment, Object Classification, Precision, Recall, mAP, F1-Score, Smart Surveillance, Autonomous Vehicles, Lightweight Model

Objective. Celiac disease (CD) has emerged as a significant global public health concern, exhibiting an estimated worldwide prevalence of approximately 1%. However, existing research pertaining to domestic occurrences of CD is confined mainly to case reports and limited case analyses. Furthermore, there is a substantial population of undiagnosed patients in the Xinjiang region. This study endeavors to create a novel, high-performance, lightweight deep learning model utilizing endoscopic images from CD patients in Xinjiang as a dataset, with the intention of enhancing the accuracy of CD diagnosis. Approach. In this study, we propose a novel CNN-Transformer hybrid architecture for deep learning, tailored to the diagnosis of CD using endoscopic images. Within this architecture, a multi-scale spatial adaptive selective kernel convolution feature attention module demonstrates remarkable efficacy in diagnosing CD. Within this module, we dynamically capture salient features within the local channel feature map that correspond to distinct manifestations of endoscopic image lesions in the CD-affected areas such as the duodenal bulb, duodenal descending segment, and terminal ileum. This process serves to extract and fortify the spatial information specific to different lesions. This strategic approach facilitates not only the extraction of diverse lesion characteristics but also the attentive consideration of their spatial distribution. Additionally, we integrate the global representation of the feature map obtained from the Transformer with the locally extracted information via convolutional layers. This integration achieves a harmonious synergy that optimizes the diagnostic prowess of the model. Main results. Overall, the accuracy, specificity, F1-Score, and precision in the experimental results were 98.38%, 99.04%, 98.66% and 99.38%, respectively. Significance. This study introduces a deep learning network equipped with both global feature response and local feature extraction capabilities. This innovative architecture holds significant promise for the accurate diagnosis of CD by leveraging endoscopic images captured from diverse anatomical sites.

Forest resources are one of the indispensable resources of the earth, which are the basis for the survival and development of human society. With the swift advancements in computer vision and artificial intelligence technology, the utilization of deep learning for smoke detection has achieved remarkable results. However, the existing deep learning models have poor performance in forest scenes and are difficult to deploy because of numerous parameters. Hence, we introduce an optimized forest fire smoke monitoring system for embedded edge devices based on a lightweight deep learning model. The model makes full use of the multi-scale variable attention mechanism of Transformer architecture to strengthen the ability of image feature extraction. Considering the needs of application scenarios, we propose an improved lightweight network model LCNet for feature extraction, which can reduce the parameters and enhance detecting ability. In order to improve running speed, a simple semi-supervised label knowledge distillation scheme is used to enhance the overall detection capability. Finally, we design and implement a forest fire smoke detection system on an embedded device, including the Jetson NX hardware platform, high-definition camera, and detection software system. The lightweight model is transplanted to the embedded edge device to achieve rapid forest fire smoke detection. Also, an asynchronous processing framework is designed to make the system highly available and robust. The improved model reduces three-fourths of the parameters and increases speed by 3.4 times with similar accuracy to the original model. This demonstrates that our system meets the precision demand and detects smoke in time.

Transient multi-indicator detection for seedling sorting in high-speed transplanting based on a lightweight model

Deep-Orga: An improved deep learning-based lightweight model for intestinal organoid detection

Deep learning for three-dimensional (3D) object classification is a promising task in digital holography. In this paper, we propose a convolutional neural network (CNN) that performs the multi-class classification of 3D objects information retrieved using off-axis Fresnel digital holography. The performance of the proposed method is evaluated for five different sets of 3D objects using loss and accuracy curves to demonstrate the proof of the concept.KeywordsDeep learningConvolutional neural network3-D objects classificationDigital holography

Lightweight deep learning models for face recognition are becoming increasingly crucial for deployment on resource‐constrained devices such as embedded systems or mobile devices. This paper presents a highly efficient and compact deep learning (DL) model that achieves state‐of‐the‐art performance on various face recognition benchmarks. The developed DL model employs one‐ or few‐shot learning to obtain effective feature embeddings and draws inspiration from FaceNet with significant refinements to achieve a memory size of only 3.5 MB—about 30 times smaller than FaceNet—while maintaining high accuracy and real‐time performance. The study demonstrates the model's effectiveness through extensive experiments, which include testing on public datasets and the model's ability to recognize occluded faces in uncontrolled environments using grayscale input images. Compared to the state‐of‐the‐art lightweight models, the proposed model requires fewer FLOPs (0.06G), has a smaller number of parameters (1.2 M), and occupies a smaller model size (3.5 MB) while achieving a competitive level of recognition accuracy and real‐time performance. The results show that the model is well‐suited for deployment in embedded domains, including live entrance security checks, driver authorization, and in‐class attendance systems. The entire code of FN8 is available on GitHub .