In recent years, there has been significant development in research on methods for autonomous driving decision-making based on deep reinforcement learning, including Deep Deterministic Policy Gradient (DDPG) , Proximal Policy Optimization (PPO) , and others. Reinforcement learning strategies based on proximal policy optimization often suffer from poor performance due to getting trapped in local optima and inefficient learning. To address the challenges of proximal policy optimization in autonomous driving, we propose an autonomous driving decision-making algorithm based on adaptive curiosity mechanism and experience replay. Firstly, we introduce a mechanism for adaptive curiosity adjustment based on episode length to address the issue of local optima in proximal policy optimization. By incorporating curiosity mechanisms, the algorithm's exploratory nature is enhanced. Additionally, to ensure safety, we impose constraints on the curiosity coefficient using variations in episode length. Secondly, to overcome the low sample utilization and inefficient learning in PPO, we combine it with an experience replay mechanism, enabling faster learning of superior policies and improving learning efficiency. In simulation experiments, our algorithm efficiently explores a better and safer driving strategy.
Multitarget tracking in video surveillance is challenging because the appearance features of the target are often unreliable in complicated scenes. To solve the problem, we propose a multitarget tracking method using multifeature model with acceleration feature. First, an acceleration feature descriptor is derived from the histograms of the optical flow features according to the background difference. Our approach filters and normalizes the descriptors of consecutive frames to establish acceleration feature models. Then, the multifeature models of target templates are initialized by combining acceleration and multiple spatial feature models. Second, we implement data association based on the tracklet confidence by integrating the acceleration and multiple spatial feature affinities. As a result, the optimal associated pairs between target tracklets and detections are solved by the Hungarian algorithm. Finally, our tracking system updates the multifeature models of target templates online depending on the reliability of the tracklets, and the trajectories of multiple targets are output. Experiments conducted on the challenging multiple object tracking benchmark confirm the effectiveness and superiority of the proposed method.
The high variability of sign colors and shapes in uncontrolled environments has made the detection of traffic signs a challenging problem in computer vision. We propose a traffic sign detection (TSD) method based on coarse-to-fine cascade and parallel support vector machine (SVM) detectors to detect Chinese warning and danger traffic signs. First, a region of interest (ROI) extraction method is proposed to extract ROIs using color contrast features in local regions. The ROI extraction can reduce scanning regions and save detection time. For multiclass TSD, we propose a structure that combines a coarse-to-fine cascaded tree with a parallel structure of histogram of oriented gradients (HOG) + SVM detectors. The cascaded tree is designed to detect different types of traffic signs in a coarse-to-fine process. The parallel HOG + SVM detectors are designed to do fine detection of different types of traffic signs. The experiments demonstrate the proposed TSD method can rapidly detect multiclass traffic signs with different colors and shapes in high accuracy.
The multiview appearance of road signs in uncontrolled environments has made the detection of road signs a challenging problem in computer vision. We propose a road sign detection method to detect multiview road signs. This method is based on several algorithms, including the classical cascaded detector, the self-adaptive weighted Gaussian color model (SW-Gaussian model), and a shape context matching method. The classical cascaded detector is used to detect the frontal road signs in video sequences and obtain the parameters for the SW-Gaussian model. The proposed SW-Gaussian model combines the two-dimensional Gaussian model and the normalized red channel together, which can largely enhance the contrast between the red signs and background. The proposed shape context matching method can match shapes with big noise, which is utilized to detect road signs in different directions. The experimental results show that compared with previous detection methods, the proposed multiview detection method can reach higher detection rate in detecting signs with different directions.
Ultrasonic CT is a new technique to measure temperature distribution in air. Based on the principle of ultrasonic CT technique, and the Maximum-Likelihood Expectation-Maximization (ML-EM) iteration algorithm, a novel method of temperature distribution imaging is proposed. In this method, Gaussian distribution model is applied instead of the traditional Poisson distribution model to the ML-EM iteration algorithm. And with Gaussian distribution, a new kind of ML-EM iteration algorithm is proposed. Using this method, the ultrasonic speed matrix can be calculated from projection data on a number of fixed propagation paths. And the 3D temperature distribution is obtained from the speed information. The simulation results prove the correctness and the validity of the proposed method.
We present a visual tracking method with feature fusion via joint sparse presentation. The proposed method describes each target candidate by combining different features and joint sparse representation for robustness in coefficient estimation. Then, we build a probabilistic observation model based on the approximation error between the recovered candidate image and the observed sample. Finally, this observation model is integrated with a stochastic affine motion model to form a particle filter framework for visual tracking. Furthermore, a dynamic and robust template update strategy is applied to adapt the appearance variations of the target and reduce the possibility of drifting. Quantitative evaluations on challenging benchmark video sequences demonstrate that the proposed method is effective and can perform favorably compared to several state-of-the-art methods.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.