Optimal Camera Placement Research Articles

Optimal Camera Placement to Generate 3D Reconstruction of a Mixed-Reality Human in Real Environments

Virtual reality and augmented reality are increasingly used for immersive engagement by utilizing information from real environments. In particular, three-dimensional model data, which is the basis for creating virtual places, can be manually developed using commercial modeling toolkits, but with the advancement of sensing technology, computer vision technology can also be used to create virtual environments. Specifically, a 3D reconstruction approach can generate a single 3D model from image information obtained from various scenes in real environments using several cameras (multi-cameras). The goal is to generate a 3D model with excellent precision. However, the rules for choosing the optimal number of cameras and settings to capture information from in real environments (e.g., actual people) employing several cameras in unconventional positions are lacking. In this study, we propose an optimal camera placement strategy for acquiring high-quality 3D data using an irregular camera placement, essential for organizing image information while acquiring human data in a three-dimensional real space, using multiple irregular cameras in real environments. Our results show that installation costs can be lowered by arranging a minimum number of multi-camera cameras in an arbitrary space, and automated virtual human manufacturing with high accuracy can be conducted using optimal irregular camera location.

A Generic and Scalable Approach to Maximize Coverage in Diverse Indoor and Outdoor Multicamera Surveillance Scenarios

Efficient deployment of cameras optimizes the costs and benefits in a multicamera surveillance network. Most camera placement algorithms are developed for surveillance regions with predefined camera locations, where optimal orientation for every given camera location is determined to maximize coverage. The existing approaches to optimizing the number of cameras, locations, and orientations focus on specific scenarios and are neither generic nor scalable across diverse surveillance scenarios. This article proposes a generic and scalable reward penalty score (RPS) algorithm for optimal camera placement in diverse indoor and outdoor scenarios to efficiently attain a specified coverage requirement. The camera placement decision is driven by maximizing total coverage over the surveillance region with a minimum number of cameras at optimal locations and orientations. Based on the RPS algorithm, we extend the existing Greedy grid voting (GGV) algorithm that was limited to optimizing camera orientations for predefined locations. The extended GGV (EGGV) algorithm is broader in scope and optimizes the number of cameras, their locations, and orientations. Overall, the RPS algorithm produces superior coverage results over indoor and outdoor scenarios compared to the existing camera placement algorithms on map images of diverse surveillance scenarios ranging from small to large.

3차원 환경 복원을 위한 다수 카메라 최적 배치 학습 기법

Recently, research and development on immersive virtual reality(VR) technology to provide a realistic experience is being widely conducted. To provide realistic experience in immersive virtual reality for VR participants, virtual environments should consist of high-realistic environments using 3D reconstruction. In this paper, to acquire 3D information in real space using multiple cameras in the reconstruction process, we propose a novel method of optimal camera placement for accurate reconstruction to minimize distortion of 3D information. Through our approach in this paper, real 3D information can obtain with minimized errors during environment reconstruction, and it is possible to provide a more immersive experience with the created virtual environment.

Commentary on “On the optimal placement of cameras for surveillance and the underlying set cover problem” [Applied Soft Computing, vol. 74, 2019, pages 133–153

In a survey article, Kritter et al. (2019) state that the optimal camera placement problem finds application in photogrammetry among many other research areas. They affirm that it has its roots in the set cover problem, which is one of Karp’s original NP-complete problems. They claim that photogrammetry’s optimal camera placement problem can trivially transform into the set cover problem. This article points out the mistake of such an idea by contrasting the mathematical definitions and goals of these two research areas. The document recalls the bundle adjustment method to achieve an accurate three-dimensional reconstruction. Then, the article recaps the idea of Kritter et al. (2019) that the research community based the analysis of camera placement on the visibility problem. Later, the paper presents network design in photogrammetry as an optimization problem based on a scheme of four design stages/questions that photogrammetrists attempt to satisfy. We finish the document by clarifying why it is not possible to reduce the optimal camera placement to the set cover problem by pointing out the mistakes made by Kritter et al. (2019) in the survey.

Visual Sensor Placement Optimization with 3D Animation for Cattle Health Monitoring in a Confined Operation.

Simple SummaryThis paper introduces a new method of finding the best locations to place video cameras inside large cattle barns to monitor the behavior and health of the animals. Current approaches to livestock video monitoring rely on mounting cameras in the most convenient places for installation, but those locations might either be impractical for actual barns and/or might not capture the best views. This work showed that there is short list of the best placement options for the cameras to choose from which will provide the best camera views.Computer vision has been extensively used for livestock welfare monitoring in recent years, and data collection with a sensor or camera is the first part of the complete workflow. While current practice in computer vision-based animal welfare monitoring often analyzes data collected from a sensor or camera mounted on the roof or ceiling of a laboratory, such camera placement is not always viable in a commercial confined cattle feeding environment. This study therefore sought to determine the optimal camera placement locations in a confined steer feeding operation. Measurements of cattle pens were used to create a 3D farm model using Blender 3D computer graphic software. In the first part of this study, a method was developed to calculate the camera coverage in a 3D farm environment, and in the next stage, a genetic algorithm-based model was designed for finding optimal placements of a multi-camera and multi-pen setup. The algorithm’s objective was to maximize the multi-camera coverage while minimizing budget. Two different optimization methods involving multiple cameras and pen combinations were used. The results demonstrated the applicability of the genetic algorithm in achieving the maximum coverage and thereby enhancing the quality of the livestock visual-sensing data. The algorithm also provided the top 25 solutions for each camera and pen combination with a maximum coverage difference of less than 3.5% between them, offering numerous options for the farm manager.

An Efficient Graph Based Approach for Reducing Coverage Loss From Failed Cameras of a Surveillance Network

The optimal placement of surveillance cameras to maximize the total coverage of camera networks is of significant research interest due to the proliferation of camera networks in diverse application scenarios. Existing camera placement algorithms are mostly designed to optimize coverage. In the event of failure of one or more cameras, these optimization algorithms reorient all the remaining cameras in the surveillance network to regain the lost coverage; and hence are not cost-effective. A simple and straightforward solution to regain the lost coverage is by reorienting the field of view of active cameras to overlap with those of the damaged cameras. In this paper, we propose the Visibility Graph Reduction (VGR) algorithm, a novel graph-based approach to select potential cameras amongst the active cameras, that can optimally alleviate the loss in coverage resulting from the failure of one or more cameras. We validate our algorithm on map images across diverse indoor and outdoor surveillance scenarios with existing camera networks. Experimental results show that our algorithm minimizes the number of cameras that need to be reoriented, and produces similar coverage results as that of reorientating all the available active cameras in the surveillance network. Our approach is both cost-effective and computationally efficient, and thus minimizes the human effort involved in reorienting cameras across practical scenarios.

A Multiresolution Approach for Large Real-World Camera Placement Optimization Problems

There have been numerous attempts at solving the optimal camera placement problem across multiple applications. Exact linear programming-based, as well as, heuristic combinatorial optimization methods were shown to be successful in providing optimal or near-optimal solutions to this problem. Working over a discrete space model is the general practice when solving the camera placement problem. However, discretized environments often limit the methods’ usage only to small-scale datasets due to resource and time constraints that grow exponentially with the number of 3D points collected from the discrete space. We propose a multi-resolution approach that enables the usage of existing optimization algorithms on large real-world problems modelled using high resolution 3D grids. Our method works by grouping together the given discrete set of possible camera locations into clusters of points, multiple times, resulting in multiple resolution levels. Camera placement optimization is repeated for all resolution levels while propagating the optimized solution from low to high resolutions. Our experiments on both simulated and real data with grids of varying sizes show that using our multi-resolution approach, existing camera placement optimization methods can be used even on high resolution grids consisting of hundreds of thousands of points. Our results also show that the strategy of grouping points together by exploiting underlying 3D geometry to optimize camera poses is not only significantly faster than optimizing on the entire set of samples but, it also provides better camera coverage.

BIM-based optimization of camera placement for indoor construction monitoring considering the construction schedule

Construction cameras have been used to support autonomous job site monitoring in recent years. However, it remains challenging to find the optimal camera placement configuration in a dynamic job site environment. To address this problem, this paper proposes a camera placement optimization framework using building information modeling (BIM). The framework considers changes in dynamic obstacles and working areas in different construction stages. Data image is used as the data mediator to connect the three modules (BIM module, mathematical module, and optimization module), visualizing the site discrete and optimized result. The efficiency of the framework is validated through the test of an indoor construction project with a size of 2000 square meters. Compared to the experience-based camera placement configuration, the optimal camera placement calculated by the proposed framework achieves 12% improvement in total coverage.

On the computational cost of the set cover approach for the optimal camera placement problem and possible set-cover-inspired trade-offs for surveillance infrastructure design

The 𝒩𝒫-hard minimum set cover problem (SCP) is a very typical model to use when attempting to formalise optimal camera placement (OCP) applications. In a generic form, the OCP problem relates to the positioning of individual cameras such that the overall network is able to cover a given area while meeting a set of application-specific requirements (image quality, redundancy, ...) and optimising an objective, typically minimum cost or maximum coverage. In this paper, we focus on an application called global or persistent surveillance: camera networks which ensure full coverage of a given area. As preliminary work, an instance generation pipeline is proposed to create OCP instances from real-world data and solve them using existing literature. The computational cost of both the instance generation process and the solving algorithms however highlights a need for more efficient methods for decision makers to use in real-world settings. In this paper, we therefore propose to review the suitability of the approach, and more specifically to question two key elements: the impact of sampling frequencies and the importance of rigid full-coverage constraints. The results allow us to quickly provide decision makers with an overview of available solutions and trade-offs.

Generative Methods for Guard and Camera Placement in Stealth Games

Enemy observers, such as cameras and guards, are common elements that provide challenge to many stealth and combat games. Defining the exact placement and movement of such entities, however, is a non-trivial process, requiring a designer balance level-difficulty, coverage, and representation of realistic behaviours. In this work we explore systems for procedurally generating both camera and guard placement in a stealth game context. For the former we use an approach based on weakening theoretical results for optimal camera placement, while for the latter we perform automatic roadmap construction, generating more specific patrol behaviours through a grammar-based technique. We evaluate both approaches with a non-trivial implementation in Unity3D, and apply quantitative metrics to demonstrate how different parametrizations can be used to control level difficulty without sacrificing believability.

Weighting-based Variable Neighborhood Search for Optimal Camera Placement

The optimal camera placement problem (OCP) aims to accomplish surveillance tasks with the minimum number of cameras, which is one of the topics in the GECCO 2020 Competition and can be modeled as the unicost set covering problem (USCP). This paper presents a weighting-based variable neighborhood search (WVNS) algorithm for solving OCP. First, it simplifies the problem instances with four reduction rules based on dominance and independence. Then, WVNS converts the simplified OCP into a series of decision unicost set covering subproblems and tackles them with a fast local search procedure featured by a swap-based neighborhood structure. WVNS employs an efficient incremental evaluation technique and further boosts the neighborhood evaluation by exploiting the dominance and independence features among neighborhood moves. Computational experiments on the 69 benchmark instances introduced in the GECCO 2020 Competition on OCP and USCP show that WVNS is extremely competitive comparing to the state-of-the-art methods. It outperforms or matches several best performing competitors on all instances in both the OCP and USCP tracks of the competition, and its advantage on 15 large-scale instances are over 10%. In addition, WVNS improves the previous best known results for 12 classical benchmark instances in the literature.

Novel greedy grid-voting algorithm for optimisation placement of multi-camera

The optimal placement of surveillance cameras and determining the configuration of exposure routes to ensure optimal coverage is essentially a combinatorial optimisation problem. In this paper, we proposed two approaches to identify and locate the location of cameras in an area of interest with planning already done at the site. The major contribution of the paper is to propose the modification on the greedy grid voting algorithm, which can control the overlap between each camera's coverage based on the application requirements. The greedy grid-voting algorithm does not follow any execution order for optimisation purposes. We also modified the traditional global greedy algorithm and it produced better coverage of the area of interest compared to the greedy approaches used to calculate the maximum coverage. The results obtained tell us that the approach ensures total coverage with a minimum of sensors than other techniques exist in the literature.

Optimal Placement and Intelligent Smoke Detection Algorithm for Wildfire-Monitoring Cameras

Smoke produced by wildfires is usually visible much earlier than flames. Hence, early detection of wildfire smoke is essential to prevent severe property losses and heavy casualties from catastrophic wildfires. Camera networks are being built and expanded to achieve timely wildfire smoke detection. To achieve the best camera coverage and detection accuracy with limited budget, an intelligent video smoke detection algorithm and an optimal wildfire camera placement strategy are in a critical need. In this paper, we propose an efficient video smoke detection framework designed for embedded applications on local cameras. It consists of two modules. In the first module, the original video frames are processed by local binary patterns and a dense optical flow estimator. In the second module, the produced features are then fed into a lightweight deep convolutional neural network, which serves as a binary classifier to detect the presence of smoke. We also formulate the wildfire camera placement problem as a binary integer programming problem to minimize the overall fire risk of a given area. Case studies on real-world videos are carried out to validate the accuracy as well as the computational and memory efficiency of the proposed smoke detection framework. We also validate our proposed camera placement strategy by simulating the deployment of wildfire cameras across a test region in Southern California.

Solving Optimal Camera Placement Problems in IoT Using LH-RPSO

With the increasing need for public security and intelligent life and the development of Internet of Things (IoT), the structure and application of vision sensor network are becoming more and more complex. It is no longer a system with simple static monitoring, but a complex system that can be used for intelligent processing, such as target localization, identification, tracking and so on. In order to accomplish various tasks efficiently, it is important to determine the deployment plan of camera network in advance. Many researches discretize the optimal camera placement problem into a binary integer programming (BIP) problem, which is NP-hard, and put forward some approximate solutions including greedy heuristics, semi-definite programming, simulated annealing, etc. In practice, however, camera parameters include both continuous values (location and orientation) and discrete values (camera type). To get a much more accurate result, we do not discretize the continuous camera parameters any more, on the contrary, we handle the continuous values in continuous domain directly. Meanwhile, a Latin Hypercube based Resampling Particle Swarm Optimization (LH-RPSO) algorithm is proposed to effectively solve the problem. To validate the proposed algorithm, we compared it with standard Particle Swarm Optimization (PSO) and Resampling Particle Swarm Optimization (RPSO). Simulation results for an outdoor planar regions illustrated the efficiency of the proposed algorithm.

Hybrid differential evolution algorithms for the optimal camera placement problem

PurposeThis paper aims to investigate to what extent hybrid differential evolution (DE) algorithms can be successful in solving the optimal camera placement problem.Design/methodology/approachThis problem is stated as a unicost set covering problem (USCP) and 18 problem instances are defined according to practical operational needs. Three methods are selected from the literature to solve these instances: a CPLEX solver, greedy algorithm and row weighting local search (RWLS). Then, it is proposed to hybridize these algorithms with two hybrid DE approaches designed for combinatorial optimization problems. The first one is a set-based approach (DEset) from the literature. The second one is a new similarity-based approach (DEsim) that takes advantage of the geometric characteristics of a camera to find better solutions.FindingsThe experimental study highlights that RWLS and DEsim-CPLEX are the best proposed algorithms. Both easily outperform CPLEX, and it turns out that RWLS performs better on one class of problem instances, whereas DEsim-CPLEX performs better on another class, depending on the minimal resolution needed in practice.Originality/valueUp to now, the efficiency of RWLS and the DEset approach has been investigated only for a few problems. Thus, the first contribution is to apply these methods for the first time in the context of camera placement. Moreover, new hybrid DE algorithms are proposed to solve the optimal camera placement problem when stated as a USCP. The second main contribution is the design of the DEsim approach that uses the distance between camera locations to fully benefit from the DE mutation scheme.

Optimal Camera Placement for Monitoring Safety in Metro Station Construction Work

Monitoring systems based on cameras are crucial for safety management of the high-risk activities common in the complex environment of metro station construction sites, and hence there is a need for a reliable camera network system. However, the number and locations of cameras are currently estimated according to the experience of managers/engineers, and the occlusion effect is rarely considered, resulting in weak coverage of 3D spaces in practice. To address this gap, a novel approach is presented to optimize camera placements for 100% site coverage while considering the occlusion dynamics caused by sidewalls and supports during excavation in metro station projects. A case study of a metro station project is presented to demonstrate and validate the approach, with results showing that the optimized plans for camera placement have larger coverage than the original plan and better performance in safety monitoring and controlling hazards. Optimized in this way, the plans for camera placement can help managers with effective planning and enhanced safety management of metro station construction sites.

On the optimal placement of cameras for surveillance and the underlying set cover problem

Given a delimited surveillance area, represented in either 2D or 3D, and a set of feasible camera locations and orientations, the optimal camera placement problem (OCP) is that of identifying camera configurations which optimise a predefined objective under a set of application-specific constraints. While this problem appears in many modern applications such as area surveillance, target tracking, photogrammetry or traffic and crowd analysis, it finds its roots in one of Karp’s 21 original NP-complete problems: set cover (SCP). If the two problems are often structurally identical, many papers dealing with optimal camera placement use this relationship implicitly, and a lot of the work done on the SCP has yet to find its way into the literature of the applied problem. In this survey, we review both in terms of problem modelling, preprocessing and solving approaches, and attempt to bring them together by suggesting open lines of research for future works.

Optimal Camera Pose and Placement Configuration for Maximum Field-of-View Video Stitching.

An optimal camera placement problem is investigated. The objective is to maximize the area of the field of view (FoV) of a stitched video obtained by stitching video streams from an array of cameras. The positions and poses of these cameras are restricted to a given set of selections. The camera array is designed to be placed inside the abdomen to support minimally invasive laparoscopic surgery. Hence, a few non-traditional requirements/constraints are imposed: Adjacent views are required to overlap to support image registration for seamless video stitching. The resulting effective FoV should be a contiguous region without any holes and should be a convex polygon. With these requirements, traditional camera placement algorithms cannot be directly applied to solve this problem. In this work, we show the complexity of this problem grows exponentially as a function of the problem size, and then present a greedy polynomial time heuristic solution that approximates well to the globally optimal solution. We present a new approach to directly evaluate the combined coverage area (area of FoV) as the union of a set of quadrilaterals. We also propose a graph-based approach to ensure the stitching requirement (overlap between adjacent views) is satisfied. We present a method to find a convex polygon with maximum area from a given polygon. Several design examples show that the proposed algorithm can achieve larger FoV area while using much less computing time.

Computer‐Aided Optimization of Surveillance Cameras Placement on Construction Sites

AbstractSurveillance system is becoming an indispensable system on construction sites with the fast development of computer vision techniques, thus an optimal placement of surveillance cameras is essential for the successful performance of this system. However, to develop effective models and solutions for large‐scale camera placement still remain as opening challenges. Therefore, this study investigated two fundamental placement problems and proposed a multiobjective placement problem, where the maximum‐coverage problem is to monitor the construction layout as much as possible with a limited budget; the minimum‐cost problem is to minimize the cost given a layout required to be fully covered; and the multiobjective problem is to identify the Pareto fronts of cost and coverage ratio of the system. To solve these problems, the objective space and search space were discretized, and the deterministic and heuristic approaches were revised and developed to provide effective solutions. Finally, experiments in a practical project in Hong Kong were conducted to verify the sufficiency of the developed algorithms and findings revealed potential implementations in many scenarios.

Parallel Preprocessing for the Optimal Camera Placement Problem

Parallel Preprocessing for the Optimal Camera Placement Problem