Privacy preserving optics for miniature vision sensors

Pittaluga, Francesco; Koppal, Sanjeev J.

doi:10.1109/cvpr.2015.7298628

Cited by 40 publications

(26 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machot et al [35] investigated on sensor data in order to discover unseen activities associated with human action recognition. Pittaluga and Koppal [36] used miniature vision sensors proposed privacy preserving optics to strike balance between utility of videos and privacy. It has many applications like motion tracking, depth sensing and blob detection.…”

Section: Related Workmentioning

confidence: 99%

Privacy preserving human activity recognition framework using an optimized prediction algorithm

Kumar¹,

Harikiran²

2022

IJ-AI

View full text Add to dashboard Cite

Human activity recognition, in computer vision research, is the area of growing interest as it has plethora of real-world applications. Inferring actions from one or more persons captured through a live video has its immense utility in the contemporary era. Same time, protecting privacy of humans is to be given paramount importance. Many researchers contributed towards this end leading to privacy preserving action recognition systems. However, having an optimized model that can withstand any adversary models that strives to disclose privacy information. To address this problem, we proposed an algorithm known optimized prediction algorithm for privacy preserving activity recognition (OPA-PPAR) based on deep neural networks. It anonymizes video content to have adaptive privacy model that defeats attacks from adversaries. The privacy model enhances the privacy of humans while permitting highly accurate approach towards action recognition. The algorithm is implemented to realize privacy preserving human activity recognition framework (PPHARF). The visual recognition of human actions is made using an underlying adversarial learning process where the anonymization is optimized to have an adaptive privacy model. A dataset named human metabolome database (HMDB51) is used for empirical study. Our experiments with using Python data science platform reveal that the OPA-PPAR outperforms existing methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Privacy preserving human activity recognition framework using an optimized prediction algorithm

Kumar¹,

Harikiran²

2022

IJ-AI

View full text Add to dashboard Cite

show abstract

“…In other words, a set of identical mirror viewing directions, by with consecutively increasing concentric FOVs would keep increasing the value but would redundantly cover the same angular region. Our solution: We adapt a previous effort in computer vision for an optical knapsack algorithm [46] and present an attention knapsack algorithm that takes into account angular coverage by discretizing the field-of-view into β angular regions, each with a solid angle of π β . Our key idea, inspired from [46], is to create a binary array that keeps track of the overlap of each mirror viewing direction, and the update to this does not affect the overall running time of the algorithm.…”

Section: Feasible Fovea From the Attention Maskmentioning

confidence: 99%

“…Our solution: We adapt a previous effort in computer vision for an optical knapsack algorithm [46] and present an attention knapsack algorithm that takes into account angular coverage by discretizing the field-of-view into β angular regions, each with a solid angle of π β . Our key idea, inspired from [46], is to create a binary array that keeps track of the overlap of each mirror viewing direction, and the update to this does not affect the overall running time of the algorithm. We call this array K(n, β) where K(i, b) = 1 if the corresponding mirror viewing direction covers this angle and is 0 if it does not.…”

Section: Feasible Fovea From the Attention Maskmentioning

confidence: 99%

SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing

Tilmon

Koppal

2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

View full text Add to dashboard Cite

Figure 1: SaccadeCam: Given limited bandwidth, we adaptively distribute resolution onto regions of interest (fovea) as well as onto a low resolution wide-angle image. In (a) we show the low-res image, and we in (b) train a self-supervised network to produce attention masks. The remaining bandwidth is allocated onto fovea using this attention mask, rendering a monocular SaccadeCam image (c) from which depth estimation can occur (d). In Table 3 and Fig. 3, we show how SaccadeCam provides superior depth results to the conventional, uniformly distributed bandwidth.

show abstract

“…Ultimately they determined that there is no 'one size fits all' solution for every scenario, and object size or security context can influence the optimal method. Pittaluga and Koppal [65] have implemented a similar blur-based privacy approach within the context of micro-scale image sensors. A hardware-based approach is used to add blur, as opposed to a software-based Gaussian blur.…”

Section: Introductionmentioning

confidence: 99%

The Security-Utility Trade-off for Iris Authentication and Eye Animation for Social Virtual Avatars

John

Jörg

Koppal

et al. 2020

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

The gaze behavior of virtual avatars is critical to social presence and perceived eye contact during social interactions in Virtual Reality. Virtual Reality headsets are being designed with integrated eye tracking to enable compelling virtual social interactions. This paper shows that the near infra-red cameras used in eye tracking capture eye images that contain iris patterns of the user. Because iris patterns are a gold standard biometric, the current technology places the user's biometric identity at risk. Our first contribution is an optical defocus based hardware solution to remove the iris biometric from the stream of eye tracking images. We characterize the performance of this solution with different internal parameters. Our second contribution is a psychophysical experiment with a same-different task that investigates the sensitivity of users to a virtual avatar's eye movements when this solution is applied. By deriving detection threshold values, our findings provide a range of defocus parameters where the change in eye movements would go unnoticed in a conversational setting. Our third contribution is a perceptual study to determine the impact of defocus parameters on the perceived eye contact, attentiveness, naturalness, and truthfulness of the avatar. Thus, if a user wishes to protect their iris biometric, our approach provides a solution that balances biometric protection while preventing their conversation partner from perceiving a difference in the user's virtual avatar. This work is the first to develop secure eye tracking configurations for VR/AR/XR applications and motivates future work in the area.

show abstract

Privacy preserving optics for miniature vision sensors

Cited by 40 publications

References 67 publications

Privacy preserving human activity recognition framework using an optimized prediction algorithm

Privacy preserving human activity recognition framework using an optimized prediction algorithm

SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing

The Security-Utility Trade-off for Iris Authentication and Eye Animation for Social Virtual Avatars

Contact Info

Product

Resources

About