The automatic detection of humans in aerial thermal imagery plays a significant role in various real-time applications, such as surveillance, search and rescue and border monitoring. Small target size, low resolution, occlusion, pose, and scale variations are the significant challenges in aerial thermal images that cause poor performance for various state-of-the-art object detection algorithms. Though many deep-learning-based object detection algorithms have shown impressive performance for generic object detection tasks, their ability to detect smaller objects in the aerial thermal images is analyzed through this study. This work carried out the performance evaluation of Faster R-CNN and single-shot multi-box detector (SSD) algorithms with different backbone networks to detect human targets in aerial view thermal images. For this purpose, two standard aerial thermal datasets having human objects of varying scale are considered with different backbone networks, such as ResNet50, Inception-v2, and MobileNet-v1. The evaluation results demonstrate that the Faster R-CNN model trained with the ResNet50 network architecture out-performed in terms of detection accuracy, with a mean average precision (mAP at 0.5 IoU) of 100% and 55.7% for the test data of the OSU thermal dataset and AAU PD T datasets, respectively. SSD with MobileNet-v1 achieved the highest detection speed of 44 frames per second (FPS) on the NVIDIA GeForce GTX 1080 GPU. Fine-tuning the anchor parameters of the Faster R-CNN ResNet50 and SSD Inception-v2 algorithms caused remarkable improvement in mAP by 10% and 3.5%, respectively, for the challenging AAU PD T dataset. The experimental results demonstrated the application of Faster R-CNN and SSD algorithms for human detection in aerial view thermal images, and the impact of varying backbone network and anchor parameters on the performance improvement of these algorithms.

As a step towards enhancing users' perceived multimedia quality levels beyond the level offered by the classic audiovisual systems, the authors present the results of an experimental study which looked at user's perception of inter-stream synchronization between olfactory data (scent) and video (without relevant audio). The impact on user's quality of experience (by considering enjoyment, relevance and reality) comparing synchronous with asynchronous presentation of olfactory and video media is analyzed and discussed. The aim is to empirically define the temporal boundaries within which users perceive olfactory data and video to be synchronized. The key analysis compares the user detection and perception of synchronization error. State of the art works have investigated temporal boundaries for olfactory data with audiovisual media, but no works document the integration of olfactory data and video (with no related audio). The results of this work show that the temporal boundaries for olfactory and video only are significantly different from olfactory, video and audio. The authors conclude that the absence of contextual audio reduces considerably the acceptable temporal boundary between the scent and video. The results also indicate that olfaction before video is more noticeable to users than olfaction after video and that users are more tolerable of olfactory data after video rather than olfactory data before video. In addition the results show the presence of two main synchronization regions. This work is a step towards the definition of synchronization specifications for multimedia applications based on olfactory and video media.

Lately, significant efforts have being put into proposing various solutions for increasing multimedia viewers' perceived quality levels. One innovative avenue is to enhance users' quality of experience (QoE) by extending the classic audio-visual multimedia content to stimulate also other human senses such as olfaction, tactile, etc. In this context, this paper focuses on olfaction-enhanced multimedia content and presents the results of an experimental study which looked at user perception of inter-stream synchronization between olfactory data and video, whereby the audio used provides no contextual information. The study investigates how age and gender influence users' perception of the temporal boundaries within which they perceive olfactory data and video to be synchronized. The impact on user QoE levels (considering sense of enjoyment, relevance and reality) during synchronous and asynchronous presentations of olfactory and video media is also analyzed and discussed. The results show that there are significant differences in terms of how users of various gender and age groups perceive the skew between olfaction and video content and in their QoE levels.

Source-camera identification tools assist image forensics investigators to associate an image with a camera. The Photo Response Non-Uniformity (PRNU) noise pattern caused by sensor imperfections has been proven to be an effective way to identify the source camera. However, the PRNU is susceptible to camera settings, scene details, image processing operations (e.g., simple low-pass filtering or JPEG compression), and counter-forensic attacks. A forensic investigator unaware of malicious counter-forensic attacks or incidental image manipulation is at risk of being misled. The spatial synchronization requirement during the matching of two PRNUs also represents a major limitation of the PRNU. To address the PRNU’s fragility issue, in recent years, deep learning-based data-driven approaches have been developed to identify source-camera models. However, the source information learned by existing deep learning models is not able to distinguish individual cameras of the same model. In light of the vulnerabilities of the PRNU fingerprint and data-driven techniques, in this paper, we bring to light the existence of a new robust data-driven device-specific fingerprint in digital images that is capable of identifying individual cameras of the same model in practical forensic scenarios. We discover that the new device fingerprint is location-independent, stochastic, and globally available, which resolves the spatial synchronization issue. Unlike the PRNU, which resides in the high-frequency band, the new device fingerprint is extracted from the low- and mid-frequency bands, which resolves the fragility issue that the PRNU is unable to contend with. Our experiments on various datasets also demonstrate that the new fingerprint is highly resilient to image manipulations such as rotation, gamma correction, and aggressive JPEG compression.