A Motion Detection Algorithm Using Local Phase Information

Lazar, Aurel A.; Ukani, Nikul H.; Zhou, Yiyin

doi:10.1155/2016/7915245

Cited by 5 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we model the local phase-based motion detector (Lazar et al. 2016 ) as a DNP. This formulation provides a new insight into the structure of the local phase-based motion detector, and how phase computation can be carried out in neural circuits.…”

Section: Modeling Motion Detection With Divisive Normalization Proces...mentioning

confidence: 99%

“…In Lazar et al. ( 2016 ), we compared the two prevailing models of fly motion detection with a more complex phase-based algorithm that we devised. Under different luminance and contrast conditions, we demonstrated that (i) none of the three algorithms could fully account for motion in natural scenes, and (ii) the detection of motion was not robust at low luminance/contrast levels.…”

Section: Introductionmentioning

confidence: 99%

“…2 , we model the local phase-based motion detector devised in Lazar et al. ( 2016 ) using DNPs, and present an improved method for extracting motion velocity and derive an accuracy condition. In Sect.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Divisive normalization processors in the early visual system of the Drosophila brain

Lazar,

Zhou

2023

Biol Cybern

View full text Add to dashboard Cite

Divisive normalization is a model of canonical computation of brain circuits. We demonstrate that two cascaded divisive normalization processors (DNPs), carrying out intensity/contrast gain control and elementary motion detection, respectively, can model the robust motion detection realized by the early visual system of the fruit fly. We first introduce a model of elementary motion detection and rewrite its underlying phase-based motion detection algorithm as a feedforward divisive normalization processor. We then cascade the DNP modeling the photoreceptor/amacrine cell layer with the motion detection DNP. We extensively evaluate the DNP for motion detection in dynamic environments where light intensity varies by orders of magnitude. The results are compared to other bio-inspired motion detectors as well as state-of-the-art optic flow algorithms under natural conditions. Our results demonstrate the potential of DNPs as canonical building blocks modeling the analog processing of early visual systems. The model highlights analog processing for accurately detecting visual motion, in both vertebrates and invertebrates. The results presented here shed new light on employing DNP-based algorithms in computer vision.

show abstract

Section: Modeling Motion Detection With Divisive Normalization Proces...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Divisive normalization processors in the early visual system of the Drosophila brain

Lazar,

Zhou

2023

Biol Cybern

View full text Add to dashboard Cite

show abstract

“…In the following, we refer to this process as a Local Fourier Transform (LFT), summarized in algorithm 1. This type of analysis has already been successfully applied by Lazar et al [15] to detect motion like a Reichardt detector.…”

Section: Local Frequency Domain Transformermentioning

confidence: 99%

Local Frequency Domain Transformer Networks for Video Prediction

Farazi

Nogga

Behnke

2021

2021 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Video prediction is commonly referred to as forecasting future frames of a video sequence provided several past frames thereof. It remains a challenging domain as visual scenes evolve according to complex underlying dynamics, such as the camera's egocentric motion or the distinct motility per individual object viewed. These are mostly hidden from the observer and manifest as often highly non-linear transformations between consecutive video frames. Therefore, video prediction is of interest not only in anticipating visual changes in the real world but has, above all, emerged as an unsupervised learning rule targeting the formation and dynamics of the observed environment. Many of the deep learning-based state-of-the-art models for video prediction utilize some form of recurrent layers like Long Short-Term Memory (LSTMs) or Gated Recurrent Units (GRUs) at the core of their models. Although these models can predict the future frames, they rely entirely on these recurrent structures to simultaneously perform three distinct tasks: extracting transformations, projecting them into the future, and transforming the current frame. In order to completely interpret the formed internal representations, it is crucial to disentangle these tasks. This paper proposes a fully differentiable building block that can perform all of those tasks separately while maintaining interpretability. We derive the relevant theoretical foundations and showcase results on synthetic as well as real data. We demonstrate that our method is readily extended to perform motion segmentation and account for the scene's composition, and learns to produce reliable predictions in an entirely interpretable manner by only observing unlabeled video data.

show abstract

“…The scenarios are different where motion can be detected [5]. Firstly, recording only when motion is detected or also taking continuous inputs from video devices and another one is suspicious activity detection based on moving objects in the image frame are the main targets considered in this review [8]. 2…”

mentioning

confidence: 99%

A Review on Motion Detection Techniques

Kumbhar¹,

Bhaskar²

2017

IJTSRD

View full text Add to dashboard Cite

Motion detection is the process of detecting moving objects in background images. Motion detection plays a fundamental role in any object tracking or vide surveillance algorithm. The reliability with which potential foreground objects in movement can be identified, directly impacts on the efficiency and performance level achievable by subsequent processing stages of tracking or object recognition. The syst automatically performs a task and gives alert to security in an area. This paper represents review on Motion detection is an essential for many video applications such as video surveillance, military reconnaissance, and robotics. Most of these applications demand low power consumption, compact and lightweight design, and high speed computation platform for processing image data in real time.

show abstract

A Motion Detection Algorithm Using Local Phase Information

Cited by 5 publications

References 25 publications

Divisive normalization processors in the early visual system of the Drosophila brain

Divisive normalization processors in the early visual system of the Drosophila brain

Local Frequency Domain Transformer Networks for Video Prediction

A Review on Motion Detection Techniques

Contact Info

Product

Resources

About