Optical Flow Based on Lucas-Kanade Method for Motion Estimation

Yedjour, Hayat

doi:10.1007/978-3-030-63846-7_92

Cited by 11 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lower the MSE indicates model is closer to ground truth. In our proposed approach, MSE is minimum comparing to (BD) [46] and (BF) methods [48], demonstrating that the proposed motion boundary model and the ground-truth motion boundary are getting closer to each other.…”

Section: Motion Detection Performancementioning

confidence: 68%

“…This would occur because we wish to minimize the MSE between the two compared motion maps. The proposed approach resulted in the highest PSNR compared (BD) [46] and (BF) approaches [48].…”

Section: Motion Detection Performancementioning

confidence: 93%

“…Since this measure is used to measure the difference between two different representations of the same frame in image sequence, it is observed in Table 2, that the proposed approach gives a lesser Hausdorff distance. Therefore, the proposed model yields bet-ter performance compared to the (BD) [46] and (BF) [48] motion boundary detectors.…”

Section: Motion Detection Performancementioning

confidence: 97%

“…First, we calculate the motion information based on the Lucas-Kanade algorithm between two consecutive frames. Then, based on maximum flow present, we proceed to flow field color coding to highlight the motion estimation result and finally, a segmentation is performed on the obtained motion estimation that will be assigned to the motion boundaries computed as the gradient of the optical flow estimation (BF) [48].…”

Section: Motion Detection Performancementioning

confidence: 99%

See 3 more Smart Citations

The Hodgkin–Huxley neuron model for motion detection in image sequences

Yedjour

Meftah

Yedjour

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

In this paper, we consider a biologically-inspired spiking neural network model for motion detection. The proposed model simulates the neurons' behavior in the cortical area MT to detect different kinds of motion in image sequences. We choose the conductance-based neuron model of the Hodgkin-Huxley to define MT cell responses. Based on the center-surround antagonism of MT receptive fields, we model the area MT by its great proportion of cells with directional selective responses. The network's spiking output corresponds to an MT neuron population's firing rates and enables to extract motion boundaries. We conduct several experiments on real image sequences. The experimental results show the proposed network's ability to segregate multiple moving objects from an image sequence and reproduce the MT cells' responses. We perform a quantitative evaluation on the YouTube Motion Boundaries (YMB) dataset, and we compare the result to state-ofthe-art methods for boundary detection in videos: boundary flow estimation (BF) and temporal boundary difference (BD). The proposed network model provides the best results on YMB compared to BF and BD methods.

show abstract

Section: Motion Detection Performancementioning

confidence: 68%

“…This would occur because we wish to minimize the MSE between the two compared motion maps. The proposed approach resulted in the highest PSNR compared (BD) [46] and (BF) approaches [48].…”

Section: Motion Detection Performancementioning

confidence: 93%

Section: Motion Detection Performancementioning

confidence: 97%

Section: Motion Detection Performancementioning

confidence: 99%

See 2 more Smart Citations

The Hodgkin–Huxley neuron model for motion detection in image sequences

Yedjour

Meftah

Yedjour

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…where I x , I y , and I t are the spatial-temporal image brightness derivatives, u is the horizontal optical flow, and v is the vertical optical flow [40]. To solve this problem, [38] breaks down an image into sections denoted by Ω and then performs a weighted least-square fit of the Equation (1) to the model [u v] t shown in:…”

Section: Proposed Approachmentioning

confidence: 99%

Novel Architecture for Human Re-Identification with a Two-Stream Neural Network and Attention Mechanism

Rahi¹,

Mei²

2022

cai

View full text Add to dashboard Cite

This paper proposes a novel architecture that utilises an attention mechanism in conjunction with multi-stream convolutional neural networks (CNN) to obtain high accuracy in human re-identification (Reid). The proposed architecture consists of four blocks. First, the pre-processing block prepares the input data and feeds it into a spatial-temporal two-stream CNN (STC) with two fusion points that extract the spatial-temporal features. Next, the spatial-temporal attentional LSTM block (STA) automatically fine-tunes the extracted features and assigns weight to the more critical frames in the video sequence by using an attention mechanism. Extensive experiments on four of the most popular datasets support our architecture. Finally, the results are compared with the state of the art, which shows the superiority of this approach.

show abstract