Partially occluded pedestrian classification using histogram of oriented gradients and local weighted linear kernel support vector machine

Aly, Saleh

doi:10.1049/iet-cvi.2013.0257

Cited by 16 publications

(7 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) Bayesian Neural Network: a network that is modelled using Bayes' inference (5) to assign probabilities to events, and thus capturing uncertainties in a model's predictions, by considering the network weights as a probability distribution parameter(s) instead of a 'deterministic' number. The posterior probability of the weights given the (a) From left to right: temperature scaling [27], confidence penalty and label smoothing [28].…”

Section: Regularizationmentioning

confidence: 99%

“…R EMARKABLE advances in computing hardware, sensors and machine learning techniques have contributed significantly to artificial perception for autonomous driving [1], [2]. However, even with such progresses, artificial perception in real-world driving still meets grand challenges [1], [3]- [5]. Object detection is a key aspect of perception systems and has been gradually dominated by deep learning (DL) approaches.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Probabilistic Approach for Road-Users Detection

Melotti¹,

Lu²,

Conde³

et al. 2021

Preprint

View full text Add to dashboard Cite

Object detection in autonomous driving applications implies that the detection and tracking of semantic objects are commonly native to urban driving environments, as pedestrians and vehicles. One of the major challenges in state-of-the-art deep-learning based object detection is false positive which occurrences with overconfident scores. This is highly undesirable in autonomous driving and other critical roboticperception domains because of safety concerns. This paper proposes an approach to alleviate the problem of overconfident predictions by introducing a novel probabilistic layer to deep object detection networks in testing. The suggested approach avoids the traditional Sigmoid or Softmax prediction layer which often produces overconfident predictions. It is demonstrated that the proposed technique reduces overconfidence in the false positives without degrading the performance on the true positives. The approach is validated on the 2D-KITTI objection detection through the YOLOV4 and SECOND (Lidar-based detector). The proposed approach enables enabling interpretable probabilistic predictions without the requirement of re-training the network and therefore is very practical.

show abstract

Section: Regularizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Probabilistic Approach for Road-Users Detection

Melotti¹,

Lu²,

Conde³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Person identification using biometric recognition is one of the major research fields to address the challenges in fields such as banking, immigration and forensic labs (Charfi et al , 2016; Aly, 2014). Detection of the person’s identity can be done in the traditional way (handwriting and signature) and the biometric way.…”

Section: Introductionmentioning

confidence: 99%

HE-Co-HOG and k-SVM classifier for finger knuckle and palm print-based multimodal biometric recognition

Veluchamy¹,

Karlmarx

2020

View full text Add to dashboard Cite

Purpose Biometric identification system has become emerging research field because of its wide applications in the fields of security. This study (multimodal system) aims to find more applications than the unimodal system because of their high user acceptance value, better recognition accuracy and low-cost sensors. The biometric identification using the finger knuckle and the palmprint finds more application than other features because of its unique features. Design/methodology/approach The proposed model performs the user authentication through the extracted features from both the palmprint and the finger knuckle images. The two major processes in the proposed system are feature extraction and classification. The proposed model extracts the features from the palmprint and the finger knuckle with the proposed HE-Co-HOG model after the pre-processing. The proposed HE-Co-HOG model finds the Palmprint HE-Co-HOG vector and the finger knuckle HE-Co-HOG vector. These features from both the palmprint and the finger knuckle are combined with the optimal weight score from the fractional firefly (FFF) algorithm. The layered k-SVM classifier classifies each person's identity from the fused vector. Findings Two standard data sets with the palmprint and the finger knuckle images were used for the simulation. The simulation results were analyzed in two ways. In the first method, the bin sizes of the HE-Co-HOG vector were varied for the various training of the data set. In the second method, the performance of the proposed model was compared with the existing models for the different training size of the data set. From the simulation results, the proposed model has achieved a maximum accuracy of 0.95 and the lowest false acceptance rate and false rejection rate with a value of 0.1. Originality/value In this paper, the multimodal biometric recognition system based on the proposed HE-Co-HOG with the k-SVM and the FFF is developed. The proposed model uses the palmprint and the finger knuckle images as the biometrics. The development of the proposed HE-Co-HOG vector is done by modifying the Co-HOG with the holoentropy weights.

show abstract

“…Time, t Some examples of applications which have data that takes the form of a time series are fluid dynamics [33], electromagnetics [34], image reconstruction [35,36], power systems [37], and motion and position monitoring [38].…”

Section: Time Series Data Representationmentioning

confidence: 99%

“…DFT is used to reduce dimensionality by considering only a subset of coefficients and then normalized allows for invariance to rotation and starting points [47]. Methods of representation of time series based on FT have been applied in applications such as fluid dynamics [33], electromagnetics [34], image reconstruction [35,36]. In image recognition, such as finding similar images from a query in a database, filtering techniques can be used to account for variations which don't factor into the decisions, such as the orientation of a shape [42,47].…”

Section: Fourier Transformationmentioning

confidence: 99%

Representation and Analysis of Multi-Modal, Nonuniform Time Series Data: An Application to Survival Prognosis of Oncology Patients in an Outpatient Setting

Winikus¹

View full text Add to dashboard Cite

Partially occluded pedestrian classification using histogram of oriented gradients and local weighted linear kernel support vector machine

Cited by 16 publications

References 39 publications

Probabilistic Approach for Road-Users Detection

Probabilistic Approach for Road-Users Detection

HE-Co-HOG and k-SVM classifier for finger knuckle and palm print-based multimodal biometric recognition

Representation and Analysis of Multi-Modal, Nonuniform Time Series Data: An Application to Survival Prognosis of Oncology Patients in an Outpatient Setting

Contact Info

Product

Resources

About