@article{SteinertStabernack2022,
  author    = {Steinert, Fritjof and Stabernack, Benno},
  title     = {Architecture of a low latency H.264/AVC video codec for robust ML based image classification how region of interests can minimize the impact of coding artifacts},
  series = {Journal of Signal Processing Systems for Signal, Image, and Video Technology},
  volume    = {94},
  journal   = {Journal of Signal Processing Systems for Signal, Image, and Video Technology},
  number    = {7},
  publisher = {Springer},
  address   = {New York},
  issn      = {1939-8018},
  doi       = {10.1007/s11265-021-01727-2},
  pages     = {693 -- 708},
  year      = {2022},
  abstract  = {The use of neural networks is considered as the state of the art in the field of image classification. A large number of different networks are available for this purpose, which, appropriately trained, permit a high level of classification accuracy. Typically, these networks are applied to uncompressed image data, since a corresponding training was also carried out using image data of similar high quality. However, if image data contains image errors, the classification accuracy deteriorates drastically. This applies in particular to coding artifacts which occur due to image and video compression. Typical application scenarios for video compression are narrowband transmission channels for which video coding is required but a subsequent classification is to be carried out on the receiver side. In this paper we present a special H.264/Advanced Video Codec (AVC) based video codec that allows certain regions of a picture to be coded with near constant picture quality in order to allow a reliable classification using neural networks, whereas the remaining image will be coded using constant bit rate. We have combined this feature with the ability to run with lowest latency properties, which is usually also required in remote control applications scenarios. The codec has been implemented as a fully hardwired High Definition video capable hardware architecture which is suitable for Field Programmable Gate Arrays.},
  language  = {en}
}
@phdthesis{Makowski2021,
  author    = {Makowski, Silvia},
  title     = {Discriminative Models for Biometric Identification using Micro- and Macro-Movements of the Eyes},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xi, 91},
  year      = {2021},
  abstract  = {Human visual perception is an active process. Eye movements either alternate between fixations and saccades or follow a smooth pursuit movement in case of moving targets. Besides these macroscopic gaze patterns, the eyes perform involuntary micro-movements during fixations which are commonly categorized into micro-saccades, drift and tremor. Eye movements are frequently studied in cognitive psychology, because they reflect a complex interplay of perception, attention and oculomotor control. A common insight of psychological research is that macro-movements are highly individual. Inspired by this finding, there has been a considerable amount of prior research on oculomotoric biometric identification. However, the accuracy of known approaches is too low and the time needed for identification is too long for any practical application. This thesis explores discriminative models for the task of biometric identification. Discriminative models optimize a quality measure of the predictions and are usually superior to generative approaches in discriminative tasks. However, using discriminative models requires to select a suitable form of data representation for sequential eye gaze data; i.e., by engineering features or constructing a sequence kernel and the performance of the classification model strongly depends on the data representation. We study two fundamentally different ways of representing eye gaze within a discriminative framework. In the first part of this thesis, we explore the integration of data and psychological background knowledge in the form of generative models to construct representations. To this end, we first develop generative statistical models of gaze behavior during reading and scene viewing that account for viewer-specific distributional properties of gaze patterns. In a second step, we develop a discriminative identification model by deriving Fisher kernel functions from these and several baseline models. We find that an SVM with Fisher kernel is able to reliably identify users based on their eye gaze during reading and scene viewing. However, since the generative models are constrained to use low-frequency macro-movements, they discard a significant amount of information contained in the raw eye tracking signal at a high cost: identification requires about one minute of input recording, which makes it inapplicable for real world biometric systems. In the second part of this thesis, we study a purely data-driven modeling approach. Here, we aim at automatically discovering the individual pattern hidden in the raw eye tracking signal. To this end, we develop a deep convolutional neural network DeepEyedentification that processes yaw and pitch gaze velocities and learns a representation end-to-end. Compared to prior work, this model increases the identification accuracy by one order of magnitude and the time to identification decreases to only seconds. The DeepEyedentificationLive model further improves upon the identification performance by processing binocular input and it also detects presentation-attacks. We find that by learning a representation, the performance of oculomotoric identification and presentation-attack detection can be driven close to practical relevance for biometric applications. Eye tracking devices with high sampling frequency and precision are expensive and the applicability of eye movement as a biometric feature heavily depends on cost of recording devices. In the last part of this thesis, we therefore study the requirements on data quality by evaluating the performance of the DeepEyedentificationLive network under reduced spatial and temporal resolution. We find that the method still attains a high identification accuracy at a temporal resolution of only 250 Hz and a precision of 0.03 degrees. Reducing both does not have an additive deteriorating effect.},
  language  = {en}
}