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

Huda, Noor Ul; Hansen, Bolette Dybkjær; Gade, Rikke; Moeslund, Thomas B.

doi:10.3390/s20071982

Cited by 24 publications

(25 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach was tested on the OSU thermal pedestrian [14], OSU colour thermal [16], and Terravic motion IR [33] datasets. Recently, Huda, Noor Ul, et al [7] used a YOLO object detector for person detection in the thermal spectrum. The authors had created their outdoor thermal dataset for transfer learning the YOLO-v3.…”

Section: A Object Detection In Thermal Spectrum Using Multimodal and Deep Learning Methodsmentioning

confidence: 99%

“…This drawback reduces the generalization of object detectors. Furthermore, some of the thermal datasets available for roadside object detection are mainly captured from the frontal view [7]. To overcome such complexities four different thermal public datasets are employed for including sufficient data diversity and robust training of deep learning models as shown in Table I.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Object Detection in Thermal Spectrum for Advanced Driver-Assistance Systems (ADAS)

Farooq¹,

Corcoran

Rotariu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

AI-based smart thermal perception systems can cater to the limitations of conventional imaging sensors by providing a more reliable data source in low-lighting conditions and adverse weather conditions. This research evaluates and modifies the state-of-the-art object detection and classifier framework for thermal vision with seven key object classes in order to provide superior thermal sensing and scene understanding input for advanced driver-assistance systems (ADAS). The networks are trained on public datasets and is validated on test data with three different test approaches which include test-time augmentation, test-time with no augmentation, and test-time with model ensembling. Additionally, a new model ensemble-based inference engine is proposed, and its efficacy is tested on locally gathered novel test data comprising of 20K thermal frames captured with an uncooled LWIR prototype thermal camera in challenging weather and environmental scenarios. The performance analysis of trained models is investigated by computing precision, recall, and mean average precision scores (mAP). Furthermore, the smaller network variant of thermal-YOLO architecture is optimized using TensorRT inference accelerator, which is then deployed on GPU and resourceconstrained edge hardware Nvidia Jetson Nano. This is implemented to explicitly reduce the inference time on GPU as well as on Nvidia Jetson Nano to evaluate the feasibility for added real-time onboard installations.

show abstract

Section: A Object Detection In Thermal Spectrum Using Multimodal and Deep Learning Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Object Detection in Thermal Spectrum for Advanced Driver-Assistance Systems (ADAS)

Farooq¹,

Corcoran

Rotariu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Approximating the histogram or assuming a distribution might over-fit images from one database. Some methods depend on the creation and extraction of features that are fed into a binary-object/non-object-classifier [21][22][23][24][25][26][27][28][29]. Zhao et al [21] placed more emphasis on underlying temperature information in infrared images and trained a temperature net for pedestrian detection.…”

Section: Related Workmentioning

confidence: 99%

Automatic Dynamic Range Adjustment for Pedestrian Detection in Thermal (Infrared) Surveillance Videos

Oluyide

Tapamo

Walingo

2022

Sensors

View full text Add to dashboard Cite

This paper presents a novel candidate generation algorithm for pedestrian detection in infrared surveillance videos. The proposed method uses a combination of histogram specification and iterative histogram partitioning to progressively adjust the dynamic range and efficiently suppress the background of each video frame. This pairing eliminates the general-purpose nature associated with histogram partitioning where chosen thresholds, although reasonable, are usually not suitable for specific purposes. Moreover, as the initial threshold value chosen by histogram partitioning is sensitive to the shape of the histogram, specifying a uniformly distributed histogram before initial partitioning provides a stable histogram shape. This ensures that pedestrians are present in the image at the convergence point of the algorithm. The performance of the method is tested using four publicly available thermal datasets. Experiments were performed with images from four publicly available databases. The results show the improvement of the proposed method over thresholding with minimum-cross entropy, the robustness across images acquired under different conditions, and the comparable results with other methods in the literature.

show abstract

“…In general, though existing methods on human detection and tracking are quite mature in RGB datasets, studies applying them in thermal datasets like [51][52][53] are few and far between. This situation makes our research with the thermal camera more essential.…”

Section: Detection and Trackingmentioning

confidence: 99%

Clothing Insulation Rate and Metabolic Rate Estimation for Individual Thermal Comfort Assessment in Real Life

Liu

Foged

Moeslund

2022

Sensors

Self Cite

View full text Add to dashboard Cite

Satisfactory indoor thermal environments can improve working efficiencies of office staff. To build such satisfactory indoor microclimates, individual thermal comfort assessment is important, for which personal clothing insulation rate (Icl) and metabolic rate (M) need to be estimated dynamically. Therefore, this paper proposes a vision-based method. Specifically, a human tracking-by-detection framework is implemented to acquire each person’s clothing status (short-sleeved, long-sleeved), key posture (sitting, standing), and bounding box information simultaneously. The clothing status together with a key body points detector locate the person’s skin region and clothes region, allowing the measurement of skin temperature (Ts) and clothes temperature (Tc), and realizing the calculation of Icl from Ts and Tc. The key posture and the bounding box change across time can category the person’s activity intensity into a corresponding level, from which the M value is estimated. Moreover, we have collected a multi-person thermal dataset to evaluate the method. The tracking-by-detection framework achieves a mAP50 (Mean Average Precision) rate of 89.1% and a MOTA (Multiple Object Tracking Accuracy) rate of 99.5%. The Icl estimation module gets an accuracy of 96.2% in locating skin and clothes. The M estimation module obtains a classification rate of 95.6% in categorizing activity level. All of these prove the usefulness of the proposed method in a multi-person scenario of real-life applications.

show abstract

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

Cited by 24 publications

References 42 publications

Object Detection in Thermal Spectrum for Advanced Driver-Assistance Systems (ADAS)

Object Detection in Thermal Spectrum for Advanced Driver-Assistance Systems (ADAS)

Automatic Dynamic Range Adjustment for Pedestrian Detection in Thermal (Infrared) Surveillance Videos

Clothing Insulation Rate and Metabolic Rate Estimation for Individual Thermal Comfort Assessment in Real Life

Contact Info

Product

Resources

About