Search

The mainstream rotated object detection primarily focus on remote sensing images. However, people detection under fisheye images, compared to remote sensing image detection tasks, often faces significant occlusion phenomena. Currently, there is a lack of comprehensive research specifically targeting occlusion issues in overhead fisheye images. Therefore, this paper proposes an occlusion-aware rotated people detection in overhead fisheye images. To address the prevalent occlusion problem in overhead fisheye images, we design a rotated detection network model based on YOLOv8. In the network structure, AFPN is introduced into the Neck of YOLOv8 to improve the network's feature extraction capability. We propose a mechanism for allocating positive and negative samples based on the Center Distance Intersection over Union (CDIoU) and incorporate Center Distance Loss into the regression loss function. Lastly, we design a training strategy for fisheye images and introduce DIoU-NMS to further enhance the robustness against occlusion issues. Experimental results demonstrate the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

The detection of people in urban environments from satellite imagery can be employed in a variety of applications, such as urban planning, business management, crisis management, military operations, and security. A WorldView-3 satellite image of Prague was processed. Several variants of feature-extracting networks, referred to as backbone networks, were tested alongside the Faster R–CNN model. This model combines region proposal networks with object detection, offering a balance between speed and accuracy that is well suited for dense and varied urban environments. Data augmentation was used to increase the robustness of the models, which contributed to the improvement of classification results. Achieving a high level of accuracy is an ongoing challenge due to the low spatial resolution of available imagery. An F1 score of 54% was achieved using data augmentation, a 15 cm buffer, and a maximum distance limit of 60 cm. [ABSTRACT FROM AUTHOR]

Due to the severe distortion of the fisheye image, the rectangular bounding box contain a lot of invalid information. So the multi-point representation method are emerging. However, it will fail in some extreme cases especially when the center of the object is not in the instance. In this work, we propose a Convex Hull Regression Strategy for people detection on top-view fisheye images. It replaces the instance with its convex hull to solve the above challenging issue and can be pre-trained on regular datasets without additional processing. In addition, the mosaic and mixup data augmentation methods that perform well under rectangular boxes are applied to our representation. Finally, we improve the label assignment and propose a more reasonable loss function called PDIoU loss so as to focus on the overall IoU between ground truth polygon and predicted polygon. Experimental results demonstrate that our method outperforms state-of-the-art algorithms. Source code is available at https://github.com/xiaoxuebajie/CHRS. [ABSTRACT FROM AUTHOR]

Monitoring the number of people in various spaces of a building is important for optimizing space usage, assisting with public safety, and saving energy. Diverse approaches have been developed for different end goals, from ID card readers for space management, to surveillance cameras for security, to CO2 sensing for HVAC control. In the last few years, fisheye cameras mounted overhead have become the sensing modality of choice because they offer large-area coverage and significantly-reduced occlusions but research efforts are still nascent. In this paper, we provide an overview of recent research efforts in this area and propose one new direction. First, we identify benefits and challenges related to inference from top-view fisheye images, and summarize key public datasets. Then, we review efforts in algorithm development for detecting people from a single fisheye frame and from a group of sequential frames. Finally, we focus on counting people indoors. While this is straightforward for a single camera, when multiple cameras are used to monitor a space, person re-identification is needed to avoid overcounting. We describe a framework for people counting using two cameras and demonstrate its effectiveness in a large classroom for location-based person re-identification. To support people counting in even larger spaces, we propose two new person re-identification algorithms using N > 2 overhead fisheye cameras. We provide ample experimental results throughout the paper.

The detection of people in urban environments from satellite imagery can be employed in a variety of applications, such as urban planning, business management, crisis management, military operations, and security. A WorldView-3 satellite image of Prague was processed. Several variants of feature-extracting networks, referred to as backbone networks, were tested alongside the Faster R–CNN model. This model combines region proposal networks with object detection, offering a balance between speed and accuracy that is well suited for dense and varied urban environments. Data augmentation was used to increase the robustness of the models, which contributed to the improvement of classification results. Achieving a high level of accuracy is an ongoing challenge due to the low spatial resolution of available imagery. An F1 score of 54% was achieved using data augmentation, a 15 cm buffer, and a maximum distance limit of 60 cm.

The contagious disease COVID 19 (Corona Virus Disease 2019) which is caused by the novel CORONA virus has imposed lot of restrictions on the civilian movements within and between the countries. The WHO (World Health Organization) has passed a strict imposition to follow Social Distancing (SD) in order to prevent the spread of the disease. SD is nothing but keeping a least separation of 2 meters or 6 foot between the individuals in public places. Also, SD emphases on no contact or minimum contact between the people who are not from your household. The vaccination against COVID 19 disease might require a sufficient amount of time (few months to a year). Hence SD is the only current non pharmaceutical solution to curb the spread of this pandemic. On the other hand, the common people are not used to practice SD and maintain a safety bubble of 2m around them always. Hence there is a requirement of an automatic system that could help maintain the required SD without much difficulty. The object detection techniques are playing an important role in detecting various common objects that are seen in our day to day life. YOLO is the recent and real time object detection technology. In the field of computer vision, object identification is thought to be one of the most challenging tasks. In YOLO with a single evaluation, the bounding boxes and class probabilities are anticipated using only one neural network from the images directly. In the meantime, frame detection is treated as a regression problem. The intended scheme utilizes inverse perspective mapping and YOLOv3 based algorithm for detection of people accurately and to implement social distancing. [ABSTRACT FROM AUTHOR]

Pyroelectric infrared sensors (PIR) are widely used as infrared (IR) detectors due to their basic implementation, low cost, low power, and performance. Combined with a Fresnel lens, they can be used as a binary detector in applications of presence and motion control. Furthermore, due to their features, they can be used in autonomous intelligent devices or included in robotics applications or sensor networks. In this work, two neural processing architectures are presented: (1) an analog processing approach to achieve the behavior of a presynaptic neuron from a PIR sensor. An analog circuit similar to the leaky integrate and fire model is implemented to be able to generate spiking rates proportional to the IR stimuli received at a PIR sensor. (2) An embedded postsynaptic neuron where a spiking neural network matrix together with an algorithm based on digital processing techniques is introduced. This structure allows connecting a set of sensors to the post-synaptic circuit emulating an optic nerve. As a case study, the entire neural processing approach presented in this paper is applied to optical flow detection considering a four-PIR array as input. The results validate both the spiking approach for an analog sensor presented and the ability to retrieve the analog information sent as spike trains in a simulated optic nerve. [ABSTRACT FROM AUTHOR]

Plant diseases prediction is the essential technique to prevent the yield loss and gain high production of agricultural products. The monitoring of plant health continuously and detecting the diseases is a significant for sustainable agriculture. Manual system to monitor the diseases in plant is time consuming and report a lot of errors. There is high demand for technology to detect the plant diseases automatically. Recently image processing approach and deep learning approach are highly invited in detection of plant diseases. The diseases like late blight, bacterial spots, spots on Septoria leaf and yellow leaf curved are widely found in plants. These are the main reasons to affects the plants life and yield. To identify the diseases earliest, our research presents the hybrid method by combining the region based convolutional neural network (RCNN) and region based fully convolutional networks (RFCN) for classifying the diseases. First the leaf images of plants are collected and preprocessed to remove noisy data in image. Further data normalization, augmentation and removal of background noises are done. The images are divided as testing and training, training images are fed as input to deep learning architecture. First, we identify the region of interest (RoI) by using selective search. In every region, feature of convolutional neural network (CNN) is extracted independently for further classification. The plants such as tomato, potato and bell pepper are taken for this experiment. The plant input image is analyzed and classify as healthy plant or unhealthy plant. If the image is detected as unhealthy, then type of diseases the plant is affected will be displayed. Our proposed technique achieves 98.5% of accuracy in predicting the plant diseases. [ABSTRACT FROM AUTHOR]

People detection in images has many uses today, ranging from face detection algorithms used by social networks to help the users tag other people, to surveillance systems that can create a statistic of the population density in an area, or identify a suspect, or even in the automotive industry as part of the Pedestrian Crash Avoidance Mitigation (PCAM) system. This work focuses on creating a fast and reliable object detection algorithm that will be trained on scenes that depict people in an indoor environment, starting from an existing state-of-the-art approach. The proposed method improves upon the You Only Look Once version 4 (YOLOv4) network by adding a region of interest classification and regression branch such as Faster R-CNN's head. The candidate bounding boxes proposed by YOLOv4 are ranked based on their confidence score, the best candidates being kept and sent as input to the Faster Region-Based Convolutional Neural Network (R-CNN) head. To keep only the best detections, non-maximum suppression is applied to all proposals. This decreases the number of false-positive candidate bounding boxes, the low-confidence detections of the regression and classification branch being eliminated by the detections of YOLOv4 and vice versa in the non-maximum suppression step. This method can be used as the object detection algorithm in an image-based people tracking system, namely Tracktor, having a higher inference speed than Faster R-CNN. Our proposed method manages to achieve an overall accuracy of 95% and an inference time of 22 ms. [ABSTRACT FROM AUTHOR]

Human detection in the wild is a research topic of paramount importance in computer vision, and it is the starting step for designing intelligent systems oriented to human interaction thatwork in complete autonomy. To achieve this goal, computer vision and machine learning should aim at superhuman capabilities. In this work, we address the problem of fine-grained human analysis under occlusions and perspective constraints. More specifically, we discuss some issues and some possible solutions to effectively detect people using pose estimation methods and to detect humans under occlusions both in the two-dimensional (2D) image plane and in the 3D space exploiting single monocular cameras. Dealing with occlusion can be done at the joint level or pixel level: We discuss two different solutions, the former based on a supervised neural network architecture for detecting occluded joints and the latter based on a semi-supervised specialized GAN that exploits both appearance and human shape attributes to determine the missing parts of the visible shape. To deal with perspective constraints, we further discuss a neural approach based on a double architecture that learns to create an optimal neural representation, which is useful to reconstruct the 3D position of human keypoints starting with simple RGB images. All these approaches have a critical point in common: the need for large annotated datasets. To have large, fair, consistent, transparent, and ethical datasets, we propose the adoption of synthetic datasets as, for example, JTA and MOTSynth. In this article, we discuss the pros and cons of using synthetic datasets while tackling several human-centered AI issues with respect to European GDPR rules for privacy.We further explore and discuss an application in the field of risk assessment by space occupancy estimation during the COVID-19 pandemic called Inter-Homines. [ABSTRACT FROM AUTHOR]

In image detection processes where there is a variation in brightness between pixels, techniques are required to obtain optimal and adaptable threshold values for these variations. Therefore, a comparison between the binary thresholding technique and the adaptive method of Otsu is made, in videos with dynamic and static background, weighing the response time of the algorithm, memory used, requirement of the central processing unit and hits in the detections, in the languages of Python and M (Matlab). The techniques in Python present better results in terms of response time and memory space; while, when using Matlab, the lowest percentage of machine requirement is presented. Also, the Otsu method improves the percentage of hits in 12.89 % and 11.3 % for videos with dynamic and static background, with respect to the binary thresholding technique. [ABSTRACT FROM AUTHOR]

At the turn of February and March 2020, COVID-19 pandemic reached Europe. Many countries, including Poland imposed lockdown as a method of securing social distance between potentially infected. Stay-at-home orders and movement control within public space not only affected the touristm industry, but also the everyday life of the inhabitants. The hourly time-lapse from four HD webcams in Cracow (Poland) are used in this study to estimate how pedestrian activity changed during COVID-19 lockdown. The collected data covers the period from 9 June 2016 to 19 April 2020 and comes from various urban zones. One zone is tourist, one is residential and two are mixed. In the first stage of the analysis, a state-of-the-art machine learning algorithm (YOLOv3) is used to detect people. Additionally, a non-standard application of the YOLO method is proposed, oriented to the images from HD webcams. This approach (YOLOtiled) is less prone to pedestrian detection errors with the only drawback being the longer computation time. Splitting the HD image into smaller tiles increases the number of detected pedestrians by over 50%. In the second stage, the analysis of pedestrian activity before and during the COVID-19 lockdown is conducted for hourly, daily and weekly averages. Depending on the type of urban zone, the number of pedestrians decreased from 33% in residential zones to 85% in tourist zones located in the Old Town. The presented method allows for more efficient detection and counting of pedestrians from HD time-lapse webcam images compared to SSD, YOLOv3 and Faster R-CNN. The result of the research is a published database with the detected number of pedestrians from the four-year observation period for four locations in Cracow.

In this paper, we introduce an intelligent light detection and localization (LiDAL) system that uses artificial neural networks (ANN). The LiDAL systems of interest are MIMO LiDAL and MISO IMG LiDAL systems. A trained ANN with the LiDAL system of interest is used to distinguish a human (target) from the background obstacles (furniture) in a realistic indoor environment. In the LiDAL systems, the received reflected signals in the time domain have different patterns corresponding to the number of targets and their locations in an indoor environment. The indoor environment with background obstacles (furniture) appears as a set of patterns in the time domain when the transmitted optical signals are reflected from objects in LiDAL systems. Hence, a trained neural network that has the ability to classify and recognize the received signal patterns can distinguish the targets from the background obstacles in a realistic environment, especially given the mobility of targets (humans) which distinguishes them from static obstacles (furniture). The LiDAL systems with ANN are evaluated in a realistic indoor environment through computer simulation.

In this paper, we present the first indoor light-based detection and localization system that builds on concepts from radio detection and ranging (radar) making use of the expected growth in the use and adoption of visible light communication (VLC), which can provide the infrastructure for our Light Detection and Localization (LiDAL) system. Our system enables active detection, counting, and localization of people, in addition to being fully compatible with the existing VLC systems. In order to detect human (targets), LiDAL uses the visible light spectrum. It sends pulses using a VLC transmitter and analyses the reflected signal collected by a photodetector receiver. Although we examine the use of the visible spectrum here, LiDAL can be used in the infrared spectrum and other parts of the light spectrum. We introduce LiDAL with different transmitter-receiver configurations and optimum and sub-optimum detectors considering the fluctuation of the received reflected signal from the target in the presence of Gaussian noise. We design an efficient multiple input multiple output (MIMO) LiDAL system with a wide field of view (FOV) single photodetector receiver, and also design a multiple input single output (MISO) LiDAL system with an imaging receiver to eliminate the ambiguity in target detection and localization. We develop models for the human body and its reflections and consider the impact of the color and texture of the cloth used as well as the impact of target mobility. A number of detection and localization methods are developed for our LiDAL system, including cross correlation and a background subtraction method. These methods are considered to distinguish a mobile target from the ambient reflections due to background obstacles (furniture) in a realistic indoor environment.

We address the problem of automatically detecting and tracking outdoor people. We propose to combine background subtraction based tracking with tracking-by-detection approach in a Kalman filtering framework. For the detection purpose, we use HOG detector, which detects people only in those regions suggested by background subtraction model. Since detectors may give false positives or miss targets, background subtraction is used to complement the detector outcomes.

The exponential increase in the number of COVID-19 infections around the world has prompted governments, in conjunction with medical and scientific communities, to recommend a social distance of at least two meters between people, to avoid increasing the number of infections. With the purpose of determining compliance with the measure of social distancing, a pilot test is carried out through video image processing for the people detection in open spaces in the central area of the city of Cúcuta, Colombia. The proposed method consists of the analysis of information from videos of people with static background, taken from a height of 4.5 meters, in addition to location of centroids by the method of moments and distance estimation by the euclidean method, this, by means of Python programming language. As a result, it is obtained a success in the people detection of 92.43 % and that 84.21 % of those who circulated through the video frame and transit in the central zone of the city of Cúcuta, Colombia, do not comply with the social distance of two meters recommended by the scientific community and exposed in the municipal circular 023 of 2020. [ABSTRACT FROM AUTHOR]

We present an efficient and accurate people detection approach based on deep learning to detect people attacks and intrusion in video surveillance scenarios Unlike other approaches using background segmentation and pre-processing techniques, which are not able to distinguish people from other elements in the scene, we propose WatchNet++ that is a depth-based and sequential network that localizes people in top-view depth images by predicting human body joints and pairwise connections (links) such as head and shoulders. WatchNet++ comprises a set of prediction stages and up-sampling operations that progressively refine the predictions of joints and links, leading to more accurate localization results. In order to train the network with varied and abundant data, we also present a large synthetic dataset of depth images with human models that is used to pre-train the network model. Subsequently, domain adaptation to real data is done via fine-tuning using a real dataset of depth images with people performing attacks and intrusion. An extensive evaluation of the proposed approach is conducted for the detection of attacks in airlocks and the counting of people in indoors and outdoors, showing high detection scores and efficiency. The network runs at 10 and 28 FPS using CPU and GPU, respectively. [ABSTRACT FROM AUTHOR]

People detection in images has many uses today, ranging from face detection algorithms used by social networks to help the users tag other people, to surveillance systems that can create a statistic of the population density in an area, or identify a suspect, or even in the automotive industry as part of the Pedestrian Crash Avoidance Mitigation (PCAM) system. This work focuses on creating a fast and reliable object detection algorithm that will be trained on scenes that depict people in an indoor environment, starting from an existing state-of-the-art approach. The proposed method improves upon the You Only Look Once version 4 (YOLOv4) network by adding a region of interest classification and regression branch such as Faster R-CNN’s head. The candidate bounding boxes proposed by YOLOv4 are ranked based on their confidence score, the best candidates being kept and sent as input to the Faster Region-Based Convolutional Neural Network (R-CNN) head. To keep only the best detections, non-maximum suppression is applied to all proposals. This decreases the number of false-positive candidate bounding boxes, the low-confidence detections of the regression and classification branch being eliminated by the detections of YOLOv4 and vice versa in the non-maximum suppression step. This method can be used as the object detection algorithm in an image-based people tracking system, namely Tracktor, having a higher inference speed than Faster R-CNN. Our proposed method manages to achieve an overall accuracy of 95% and an inference time of 22 ms.