05 Hybrid vision algo API

Overview

Hybrid vision algo is a high-performance algorithm library designed specifically for Event Cameras, providing a variety of advanced event denoising algorithms. This document details the usage of all public APIs in the library.

Namespace

All algorithms are located under the Shimeta::Algorithm namespace, further divided by functional modules:

• Shimeta::Algorithm::Denoise - Denoising algorithm module
• Shimeta::Algorithm::CV - Computer vision module
• Shimeta::Algorithm::CV3D - 3D vision module
• Shimeta::Algorithm::Restoration - Image restoration module

Denoising Algorithm Module (Denoise)

1. DoubleWindowFilter

The double window filter uses two circular buffers to classify CD events.

Class Definition

class DoubleWindowFilter {
public:
    explicit DoubleWindowFilter(
        const size_t bufferSize = 36,
        const size_t searchRadius = 9,
        const size_t intThreshold = 1
    );

    void initialize();
    size_t countNearbyEvents(const Metavision::EventCD &event);
    bool evaluate(const Metavision::EventCD &event);
    bool retain(const Metavision::EventCD &event) noexcept;
    std::vector<Metavision::EventCD> process_events(const std::vector<Metavision::EventCD> &events);
};

Constructor Parameters

• bufferSize: Circular buffer size (Default: 36)
• searchRadius: Search radius, maximum L1 distance to consider nearby events (Default: 9)
• intThreshold: Minimum number of nearby events to classify an event as real (Default: 1)

Main Methods

• initialize(): Initialize the filter
• countNearbyEvents(): Count the number of nearby events in the two windows
• evaluate(): Evaluate whether the event is signal or noise
• retain(): Inline method to process a single event
• process_events(): Batch process event vector

Usage Example

#include <denoise/double_window_filter.h>

// Create filter
Shimeta::Algorithm::Denoise::DoubleWindowFilter filter(36, 9, 1);
filter.initialize();

// Process single event
Metavision::EventCD event;
bool isSignal = filter.evaluate(event);

// Batch process
std::vector<Metavision::EventCD> events;
auto filteredEvents = filter.process_events(events);

2. EventFlowFilter

Noise suppression filter based on event flow density and flow velocity characteristics.

Class Definition

class EventFlowFilter {
public:
    explicit EventFlowFilter(
        const size_t bufferSize = 100,
        const size_t searchRadius = 1,
        const double floatThreshold = 20.0,
        const int64_t duration = 2000
    );

    void initialize();
    double fitEventFlow(const Metavision::EventCD &event);
    bool evaluate(const Metavision::EventCD &event);
    bool retain(const Metavision::EventCD &event) noexcept;
    std::vector<Metavision::EventCD> process_events(const std::vector<Metavision::EventCD> &events);
};

Constructor Parameters

• bufferSize: Buffer size (Default: 100)
• searchRadius: Spatial neighborhood radius (Default: 1)