Variational-Based Contour Tracking in Infrared Imagery

Zhang, Hui; Zhao, Baojun; Tang, Linbo; Li, Jianke

doi:10.1109/cisp.2009.5303802

Cited by 4 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They tested their method on the OSU thermal pedestrian database [18]. Zhang et al [4] also presented a method based on background subtraction and boundary gradients, the temporal coherence of the object area, and the region signature of the intensity distribution. They also tested their method on the OSU thermal database [18].…”

Section: Thermal Approachesmentioning

confidence: 99%

“…Visual cameras capturing visible light, as well as thermal cameras capturing infrared radiation have been utilized for person detection. Many feature based machine learning [1][2][3][4], as well as deep learning [5][6][7] approaches have been utilized to deal with the problem of person detection in thermal images. Even though thermal cameras have an advantage in outdoor person detection, due to the independence of illumination, robust detection still becomes very challenging in diverse weather and light conditions (see Figure 1) and is therefore far from a solved problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Effect of a Diverse Dataset for Transfer Learning in Thermal Person Detection

Huda

Hansen

Gade

et al. 2020

Sensors

View full text Add to dashboard Cite

Thermal cameras are popular in detection for their precision in surveillance in the dark and for privacy preservation. In the era of data driven problem solving approaches, manually finding and annotating a large amount of data is inefficient in terms of cost and effort. With the introduction of transfer learning, rather than having large datasets, a dataset covering all characteristics and aspects of the target place is more important. In this work, we studied a large thermal dataset recorded for 20 weeks and identified nine phenomena in it. Moreover, we investigated the impact of each phenomenon for model adaptation in transfer learning. Each phenomenon was investigated separately and in combination. the performance was analyzed by computing the F1 score, precision, recall, true negative rate, and false negative rate. Furthermore, to underline our investigation, the trained model with our dataset was further tested on publicly available datasets, and encouraging results were obtained. Finally, our dataset was also made publicly available.

show abstract

Section: Thermal Approachesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Effect of a Diverse Dataset for Transfer Learning in Thermal Person Detection

Huda

Hansen

Gade

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The range of applications varies from industrial uses to daily life traffic and surveillance [14]. Various methods based on thermal cameras have been proposed for person detection, such as feature extraction and threshold based methods [9,12,13,42], HOG methods [25,37], machine learning techniques [18] and deep neural networks [16,17,20]. A dataset and a trained network for people detection on outdoor thermal images have been proposed in [20].…”

Section: Related Workmentioning

confidence: 99%

Multimodal and multiview distillation for real-time player detection on a football field

Cioppa

Deliège

Huda

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Monitoring the occupancy of public sports facilities is essential to assess their use and to motivate their construction in new places. In the case of a football field, the area to cover is large, thus several regular cameras should be used, which makes the setup expensive and complex. As an alternative, we developed a system that detects players from a unique cheap and wide-angle fisheye camera assisted by a single narrow-angle thermal camera. In this work, we train a network in a knowledge distillation approach in which the student and the teacher have different modalities and a different view of the same scene. In particular, we design a custom data augmentation combined with a motion detection algorithm to handle the training in the region of the fisheye camera not covered by the thermal one. We show that our solution is effective in detecting players on the whole field filmed by the fisheye camera. We evaluate it quantitatively and qualitatively in the case of an online distillation, where the student detects players in real time while being continuously adapted to the latest video conditions.

show abstract

“…Many approaches for person recognition in thermal infrared images are dealing with strong constraints such as considering only one specific dataset, assuming a stationary camera, or detecting only moving persons [5,6,8,9,13,22,23,33,35]. The authors use own datasets for their experiments [21,31,33,36] or the OTCBVS benchmark datasets: the OSU Thermal Pedestrian Database [5,6,8,13,23,26,31,33,35], the thermal IR subset of OSU Color-Thermal Database [13,21,22,33], and the Terravic Motion IR Database [26]. Regions of interest (ROIs) are detected either with background subtraction [5,6,8,9,13,22,33,35], keypoint detectors [21], sliding window [23,26,36], or thresholding methods such as MSER [31].…”

Section: Related Workmentioning

confidence: 99%

“…In this paper, we propose an approach for person detection and localization with a moving thermal infrared camera mounted on an Unmanned Ground Vehicle (UGV). In contrast to many other papers [5,6,8,9,13,22,33,35] we avoid constraints such as the assumption of a stationary camera or the detection of persons in motion only. Moving and stationary persons can be recognized in real-time in low resolution.…”

Section: Introductionmentioning

confidence: 99%

Low Resolution Person Detection with a Moving Thermal Infrared Camera by Hot Spot Classification

Teutsch

Mueller

Huber³

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

In many visual surveillance applications the task of person detection and localization can be solved easier by using thermal long-wave infrared (LWIR) cameras which are less affected by changing illumination or background texture than visual-optical cameras. Especially in outdoor scenes where usually only few hot spots appear in thermal infrared imagery, humans can be detected more reliably due to their prominent infrared signature. We propose a two-stage person recognition approach for LWIR images: (1) the application of Maximally Stable Extremal Regions (MSER) to detect hot spots instead of background subtraction or sliding window and (2) the verification of the detected hot spots using a Discrete Cosine Transform (DCT) based descriptor and a modified Random Naïve Bayes (RNB) classifier. The main contributions are the novel modified RNB classifier and the generality of our method. We achieve high detection rates for several different LWIR datasets with low resolution videos in real-time. While many papers in this topic are dealing with strong constraints such as considering only one dataset, assuming a stationary camera, or detecting only moving persons, we aim at avoiding such constraints to make our approach applicable with moving platforms such as Unmanned Ground Vehicles (UGV).

show abstract

Variational-Based Contour Tracking in Infrared Imagery

Cited by 4 publications

References 13 publications

The Effect of a Diverse Dataset for Transfer Learning in Thermal Person Detection

The Effect of a Diverse Dataset for Transfer Learning in Thermal Person Detection

Multimodal and multiview distillation for real-time player detection on a football field

Low Resolution Person Detection with a Moving Thermal Infrared Camera by Hot Spot Classification

Contact Info

Product

Resources

About