Autonomous Audio-Supported Learning of Visual Classifiers for Traffic Monitoring

Bischof, Horst; Godec, Martin; Leistner, Christian; Rinner, Bernhard; Starzacher, Andreas

doi:10.1109/mis.2010.28

Cited by 18 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the detection rate of these approaches is usually affected by occlusions and difficult weather conditions. Therefore, in [2] multiple sensor data is exploited and classification rates are improved by co-training.…”

Section: Background and Related Workmentioning

confidence: 99%

Robust Traffic State Estimation on Smart Cameras

Pletzer

Tusch

Böszörményi

et al. 2012

2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance

Self Cite

View full text Add to dashboard Cite

This paper presents a novel method for video-based traffic state detection on motorways performed on smart cameras. Camera calibration parameters are obtained from the known length of lane markings. Mean traffic speed is estimated from Kanade-Lucas-Tomasi (KLT) optical flow method using a robust outlier detection. Traffic density is estimated using a robust statistical counting method. Our method has been implemented on an embedded smart camera and evaluated under different road and illuminationconditions. It achieves a detection rate of more than 95% for stationary traffic.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Robust Traffic State Estimation on Smart Cameras

Pletzer

Tusch

Böszörményi

et al. 2012

2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance

Self Cite

View full text Add to dashboard Cite

show abstract

“…The motivation of this research is based on our previous work on traffic monitoring [Pletzer et al 2012;Bischof et al 2010] and the development of a mobile, multi-camera traffic surveillance system [Khan et al 2011]. In contrast to most of the existing traffic surveillance systems which are mostly based on fixed installations and large sensors, our portable platform can be easily deployed and used for various monitoring tasks, including law enforcement and construction site monitoring.…”

Section: Introductionmentioning

confidence: 99%

Online learning of timeout policies for dynamic power management

Khan

Rinner

2014

ACM Trans. Embed. Comput. Syst.

Self Cite

View full text Add to dashboard Cite

Dynamic power management (DPM) refers to strategies which selectively change the operational states of a device during runtime to reduce the power consumption based on the past usage pattern, the current workload, and the given performance constraint. The power management problem becomes more challenging when the workload exhibits nonstationary behavior which may degrade the performance of any single or static DPM policy.This article presents a reinforcement learning (RL)-based DPM technique for optimal selection of timeout values in the different device states. Each timeout period determines how long the device will remain in a particular state before the transition decision is taken. The timeout selection is based on workload estimates derived from a Multilayer Artificial Neural Network (ML-ANN) and an objective function given by weighted performance and power parameters. Our DPM approach is further able to adapt the powerperformance weights online to meet user-specified power and performance constraints, respectively. We have completely implemented our DPM algorithm on our embedded traffic surveillance platform and performed long-term experiments using real traffic data to demonstrate the effectiveness of the DPM. Our results show that the proposed learning algorithm not only adequately explores the power-performance trade-off with nonstationary workload but can also successfully perform online adjustment of the trade-off parameter in order to meet the user-specified constraint. ACM Reference Format: U. A. Khan and B. Rinner. 2014. Online learning of timeout policies for dynamic power management. ACM Trans. Embedd. Comput.

show abstract

“…In this article, we use a co-training strategy [2] where one classifier trains another. This approach has been applied to challenging object detection scenarios, e.g., person detection [16], vehicle detection for traffic surveillance [1] or face detection [11,20]. Similar to [1], the application target of our work is vehicle detection, although we assume a moving instead of a static platform.…”

Section: Introductionmentioning

confidence: 99%

“…This approach has been applied to challenging object detection scenarios, e.g., person detection [16], vehicle detection for traffic surveillance [1] or face detection [11,20]. Similar to [1], the application target of our work is vehicle detection, although we assume a moving instead of a static platform. A further similar point is the use of a primitive vehicle detector (laser in our case, audio in [1]).…”

Section: Introductionmentioning

confidence: 99%

“…Similar to [1], the application target of our work is vehicle detection, although we assume a moving instead of a static platform. A further similar point is the use of a primitive vehicle detector (laser in our case, audio in [1]). Our context model approach couples the global spatial scene layout ("context") to local object detection strategies.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Co-training of context models for real-time vehicle detection

Gepperth

2012

2012 IEEE Intelligent Vehicles Symposium

View full text Add to dashboard Cite

We describe a simple way to reduce the amount of required training data in context-based models of realtime object detection. We demonstrate the feasibility of our approach in a very challenging vehicle detection scenario comprising multiple weather, environment and light conditions such as rain, snow and darkness (night). The investigation is based on a real-time detection system effectively composed of two trainable components: an exhaustive multiscale object detector ("signal-driven detection"), as well as a module for generating object-specific visual attention ("context models") controlling the signal-driven detection process. Both parts of the system require a significant amount of ground-truth data which need to be generated by human annotation in a time-consuming and costly process.Assuming sufficient training examples for signal-based detection, we demonstrate that a co-training step can eliminate the need for separate ground-truth data to train context models. This is achieved by directly training context models with the results of signal-driven detection. We show that this process is feasible for different qualities of signal-driven detection, and maintains the performance gains from context models.As it is by now widely accepted that signal-driven object detection can be significantly improved by context models, our method allows to train strongly improved detection systems without additional labor, and above all, cost.

show abstract

Autonomous Audio-Supported Learning of Visual Classifiers for Traffic Monitoring

Cited by 18 publications

References 19 publications

Robust Traffic State Estimation on Smart Cameras

Robust Traffic State Estimation on Smart Cameras

Online learning of timeout policies for dynamic power management

Co-training of context models for real-time vehicle detection

Contact Info

Product

Resources

About