Detection, Estimation and Avoidance of Mobile Objects Using Stereo-Vision and Model Predictive Control

Roggeman, Hélène; Marzat, Julien; Derome, Maxime

doi:10.1109/iccvw.2017.245

Cited by 3 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second an increase to the area under view, since it is not possible for a single camera to observe large areas because of a finite sensor field of view [11]. Performance depends greatly on how closely the objects follow the established paths and the expected time intervals across cameras [17]. For scenarios in which spatio-temporal constraints cannot be used, for example, objects moving arbitrarily in the non-overlapping region, only the tracking by recognition approach can be employed, which uses the appearance and the shape of the object to recognize it when it reappears in the camera's view.…”

Section: Discussionmentioning

confidence: 99%

“…With respect to the mapping ROI models: the problem of trajectory prediction has areas of opportunity such as detection failures, objects with similar appearances, occlusions, and variations in illumination and points of view [11,20]. Only two kinds of obstacles (vehicles and pedestrians) are taken into consideration [3,11,17,20,19]. High processing runtime rate and low obstacle detection rate [3,14].…”

Section: Analysis Of Related Workmentioning

confidence: 99%

“…The fundamental step of the detection stage is to perform disparity mapping to simplify the information to be processed from the RGB channel intensity levels in the image. Disparity mapping [17] is used to obtain basic characteristics for the representation of objects in a scene in complex vehicular environments, it also has the advantage of providing spatial depth information in the scene.…”

Section: Obstacle Detection and Trajectory Estimation Proposalmentioning

confidence: 99%

See 2 more Smart Citations

Obstacle Detection and Trajectory Estimation in Vehicular Displacements based on Computational Vision

Reyes-Cocoletzi¹,

Olmos-Pineda²,

Olvera-López³

2019

RCS

View full text Add to dashboard Cite

Obstacle detection and trajectory estimation in vehicular environments is an open problem in autonomous vehicles development. The automotive industry has made significant progress in research and development of tools; however, there are still challenges to overcome and opportunity areas to be exploited in order to achieve full autonomy in vehicles. This paper presents an analysis of different methods proposed for obstacle detection and trajectory estimation, leading into a proposal of solution for solving the problem of trajectory estimation based on computer vision techniques. This proposal covers the context of traffic environments in Latin America, where basic signage (such as the dividing lines of the road) is absent or not easily visible, among other typical characteristics of countries (like Mexico and others) where the infrastructure for maintaining safe road conditions (speedbumps, potholes) is limited.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Analysis Of Related Workmentioning

confidence: 99%

Section: Obstacle Detection and Trajectory Estimation Proposalmentioning

confidence: 99%

See 1 more Smart Citation

Obstacle Detection and Trajectory Estimation in Vehicular Displacements based on Computational Vision

Reyes-Cocoletzi¹,

Olmos-Pineda²,

Olvera-López³

2019

RCS

View full text Add to dashboard Cite

show abstract

“…Then, Σ 1 (T, k + 1)and Σ 12 (T, k + 1) can be calculated faster using previous sums, and the two new measurements and storing in memory the latest N = 1 dt max i=1:n 0 (Lτ test (i)) values of each signal. The correlation c (T, k + 1) is obtained in this way using (18) with updated sums instead of re-calculating further sums at each iteration. This method significantly reduces the computational burden without any loss of accuracy and without increasing the size of the memory required to compute the time delay.…”

Section: The New Methods Of Calculating Nccmentioning

confidence: 99%

“…The many variables which can be monitored based on the optic flow include the presence of objects and obstacles and the occurrence of motion in the environment. The stereo vision implemented in previous studies using two cameras gives reliable distance [6], velocity estimates [10,15,16] or obstacle avoidance [18]. However, due to the strict limitations imposed on the energy, sensing, and processing resources of MAV drones' microprocesors, even the most efficient stereo vision methods are too computationally demanding to be implemented on-board on their microprocessors.…”

Section: Introductionmentioning

confidence: 99%

Fast normalized cross-correlation for measuring distance to objects using optic flow, applied for helicopter obstacle detection

Viel

Viollet

2021

Measurement

View full text Add to dashboard Cite

The fast normalized cross-correlation (NCC) calculation method presented here features low computational requirements, which makes it suitable for being implemented in real time onboard micro-controllers with very few computational resources. This method was adapted for making distance measurements, using a high speed optic flow sensor operating at 20m/s. An application of this study is to develop a proof of concept of an innovative optic flow sensor fixed at the tip of an helicopter's blade (from Airbus Helicopter) to measure the distance to various obstacles (wall, cliff...) in the azimuthal plane (rotor plane) during hovering flight. Due to its small size, this sensor developed in this paper can also be also adapted for Micro aerial vehicles (MAVs). This method of calculation requires less memory than the reference method, at the expense of some extra arithmetical operations, but it is still significantly lighter than the classical NCC method. An algorithm for implementing this method in real-time robotic applications is presented. Experimental results confirm the efficiency of this highly time-saving method.

show abstract

Real time obstacle motion prediction using neural network based extended Kalman filter for robot path planning

Hassan

Saleem

2022

KJS publishes peer-review articles in Mathematics, Computer Sci

View full text Add to dashboard Cite

Navigation in dynamic environments for mobile robots is a difficult problem as it involves estimating the path of moving obstacles. The measured data usually contains a bias and noise in addition to its true value. Based on a stacked denoising autoencoder (SDAE), the enhanced Kalman filter developed in this paper can estimate the obstacle position from any type of noisy input. The extended Kalman filter's ability to predict an error-free path is impacted by the measurement noise covariance matrix employed. The SDAE is a neural network topology based on deep learning that can be used to determine the optimum covariance matrix. Both Adam and stochastic gradient learning algorithms are used to train the neural network. The robot's path is re-planned based on the predicted obstacle path to ensure safe navigation. MATLAB-based numerical simulations are used to demonstrate the utility and superiority of the proposed method over the traditional Kalman filter and Particle filter methodologies. The simulation results show that in the presence of any sort of noise, the proposed technique is exceptionally durable and reliable. The simulation findings also reveal that when it comes to denoising the measured data, the stacked denoising autoencoder with Adam optimizer is more efficient than the stochastic approach. The performance of the developed algorithm is validated in MATLAB simulated environments, and it can be extended for navigation tasks. In terms of computation time and robustness in closely spaced obstacles, simulation experiments demonstrated that the path planning using the proposed algorithm outperforms the hybrid A star, artificial potential field, and decision algorithms.

show abstract

Detection, Estimation and Avoidance of Mobile Objects Using Stereo-Vision and Model Predictive Control

Cited by 3 publications

References 25 publications

Obstacle Detection and Trajectory Estimation in Vehicular Displacements based on Computational Vision

Obstacle Detection and Trajectory Estimation in Vehicular Displacements based on Computational Vision

Fast normalized cross-correlation for measuring distance to objects using optic flow, applied for helicopter obstacle detection

Real time obstacle motion prediction using neural network based extended Kalman filter for robot path planning

Contact Info

Product

Resources

About