Online decoding of Markov models under latency constraints

Narasimhan, Mukund; Viola, Paul A.; Shilman, Michael

doi:10.1145/1143844.1143927

Cited by 20 publications

(19 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work in [33] dealt with online gesture recognition using a hierarchical HMM. To achieve online recognition, the method extended the standard decoding algorithm to an online version using a variable window [37] , since the Viterbi algorithm cannot be directly applied to online scenarios.…”

Section: Online Motion Modelsmentioning

confidence: 99%

Evaluation of cupboard door sensors for improving activity recognition in the kitchen

Whitehouse

Yordanova

Lüdtke

et al. 2018

2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops)

View full text Add to dashboard Cite

Quantitative assessment of the quality of motion is increasingly in demand by clinicians in healthcare and rehabilitation monitoring of patients. We study and compare the performances of different pose representations and HMM models of dynamics of movement for online quality assessment of human motion. In a general sense, our assessment framework builds a model of normal human motion from skeleton-based samples of healthy individuals. It encapsulates the dynamics of human body pose using robust manifold representation and a first-order Markovian assumption. We then assess deviations from it via a continuous online measure. We compare different feature representations, reduced dimensionality spaces, and HMM models on motions typically tested in clinical settings, such as gait on stairs and flat surfaces, and transitions between sitting and standing. Our dataset is manually labelled by a qualified physiotherapist. The continuous-state HMM, combined with pose representation based on body-joints' location, outperforms standard discrete-state HMM approaches and other skeleton-based features in detecting gait abnormalities, as well as assessing deviations from the motion model on a frame-by-frame basis.

show abstract

Section: Online Motion Modelsmentioning

confidence: 99%

Evaluation of cupboard door sensors for improving activity recognition in the kitchen

Whitehouse

Yordanova

Lüdtke

et al. 2018

2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops)

View full text Add to dashboard Cite

show abstract

“…Technique exist for reducing latency in sequence data, such as [12], however, these focus on reducing the latency associated with decoding hidden state sequences from observed data, rather than classifying individual actions as quickly as possible.…”

Section: Related Workmentioning

confidence: 99%

Measuring and reducing observational latency when recognizing actions

Masood

Ellis

Nagaraja

et al. 2011

2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)

View full text Add to dashboard Cite

An important aspect in interactive, action-based interfaces is the latency in recognizing the action. High latency will cause the system's feedback to lag behind user actions, reducing the overall quality of the user experience. This paper presents a novel dataset and algorithms for reducing the latency in recognizing the action. Latency in classification is minimized with a classifier based on logistic regression that uses canonical poses to identify the action. The classifier is trained from the dataset using a learning formulation that makes it possible to train the classifier to reduce latency. The classifier is compared against both a Bag of Words and a Conditional Random Field classifier and is found to be superior in both pre-segmented and on-line classification tasks.

show abstract

“…The second category of application covers general signal recognition and signal processing, where HMMs operate on data in order to classify it. The latency between data input and system response is restricted and exceeding it leads to application malfunction [3][4]. This real time HMM processing is used in a wide range of applications, including speech synthesis [5] and recognition [6], image recognition, movement recognition [7], radar [8] and sonar [9][10] detection and sense-and-avoid systems.…”

Section: Introductionmentioning

confidence: 99%

FPGA implementation of logarithmic versions of Baum-Welch and Viterbi algorithms for reduced precision hidden Markov models

Pietras¹,

Klęsk²

2017

Bulletin of the Polish Academy of Sciences Technical Sciences

View full text Add to dashboard Cite

Abstract. This paper presents a programmable system-on-chip implementation to be used for acceleration of computations within hidden Markov models. The high level synthesis (HLS) and "divide-and-conquer" approaches are presented for parallelization of Baum-Welch and Viterbi algorithms. To avoid arithmetic underflows, all computations are performed within the logarithmic space. Additionally, in order to carry out computations efficiently -i.e. directly in an FPGA system or a processor cache -we postulate to reduce the floating-point representations of HMMs. We state and prove a lemma about the length of numerically unsafe sequences for such reduced precision models. Finally, special attention is devoted to the design of a multiple logarithm and exponent approximation unit (MLEAU). Using associative mapping, this unit allows for simultaneous conversions of multiple values and thereby compensates for computational efforts of logarithmic-space operations. Design evaluation reveals absolute stall delay occurring by multiple hardware conversions to logarithms and to exponents, and furthermore the experiments evaluation reveals HMMs computation boundaries related to their probabilities and floating-point representation. The performance differences at each stage of computation are summarized in performance comparison between hardware acceleration using MLEAU and typical software implementation on an ARM or Intel processor. to the network, and as the operation of the network is affected by external factors, real time computation is not guaranteed. Hence, for low latency applications, full HMM processing and computation within a dedicated embedded system is a reliable choice, and this has been shown for diverse systems such as speech recognition [11][12], pattern detection [13] and for AAV/ AUV [14]. Unfortunately, the increasing complexity of HMMs is paralleled by the growing demand for computational resources, especially memory and data throughput. Hence, when considering the hardware acceleration of HMM algorithms (forward-backward, Viterbi, Baum-Welch), the size of the HMM has to be minimized while the stability of numerical calculation still has to be guaranteed. As mentioned in [15], typical calculations associated with HMM rapidly exhaust the precision of numerical representation. This is related to the necessity of performing long sequences of multiplications of probability values (which are close to zero) for state transitions or observation emissions. Therefore, key algorithms are computed within the logarithmic space instead of applying some scaling factors [16]. Decreasing the size of an HMM can be immediately achieved by reducing the precision of its numerical representation (transition and emission matrices), e.g. down to: 32 bits (single), 16 bits (half) or 8 bits (quarter). This action directly affects and restricts the maximum length of the observation sequences examined, which means that computations on longer sequences may become numerically unstable.

show abstract

Online decoding of Markov models under latency constraints

Cited by 20 publications

References 12 publications

Evaluation of cupboard door sensors for improving activity recognition in the kitchen

Evaluation of cupboard door sensors for improving activity recognition in the kitchen

Measuring and reducing observational latency when recognizing actions

FPGA implementation of logarithmic versions of Baum-Welch and Viterbi algorithms for reduced precision hidden Markov models

Contact Info

Product

Resources

About