Files
Jungfraujoch/image_analysis/MXAnalysisWithoutFPGA.cpp
T
leonarski_f 58910274bf image_analysis: compute ROI statistics in the non-FPGA path
MXAnalysisWithoutFPGA never filled DataMessage.roi, so ROI integrals were
only available on the FPGA path. Add a software ROI engine that mirrors the
FPGA roi_calc kernel: per-ROI sum, sum of squares, good-pixel count, max and
intensity-weighted centre of mass, with each pixel carrying a 16-bit mask so
it can contribute to any subset of up to 16 ROIs.

New image_analysis/roi/ library (JFJochROIIntegration), structured like azint:
a base that precomputes the per-pixel mask and names, a templated CPU engine
(generic over pixel type for a future 16-bit path), and a GPU kernel using
per-block shared-memory atomics for the STXM case (half-detector ROIs).

Masked pixels are excluded entirely; saturated pixels are excluded from the
sums but still count towards the max, matching roi_calc exactly. The engine is
only constructed when at least one ROI is defined. Downstream CBOR/HDF5 already
consume message.roi, so no further changes are needed.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-17 21:15:54 +02:00

125 lines
6.1 KiB
C++

// SPDX-FileCopyrightText: 2024 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only
#include "MXAnalysisWithoutFPGA.h"
#include "spot_finding/StrongPixelSet.h"
#include "../compression/JFJochDecompress.h"
#include "spot_finding/SpotUtils.h"
#include "bragg_prediction/BraggPredictionFactory.h"
#include "image_preprocessing/ImagePreprocessorCPU.h"
#include "azint/AzIntEngineCPU.h"
#include "roi/ROIIntegrationCPU.h"
#include "spot_finding/ImageSpotFinderCPU.h"
#ifdef JFJOCH_USE_CUDA
#include "azint/AzIntEngineGPU.h"
#include "roi/ROIIntegrationGPU.h"
#include "spot_finding/ImageSpotFinderGPU.h"
#include "image_preprocessing/ImagePreprocessorGPU.h"
#include "image_preprocessing/ImagePreprocessorBufferGPU.h"
#include "../common/CUDAWrapper.h"
#endif
MXAnalysisWithoutFPGA::MXAnalysisWithoutFPGA(const DiffractionExperiment &in_experiment,
const AzimuthalIntegrationMapping &in_integration,
const PixelMask &in_mask,
IndexAndRefine &in_indexer)
: experiment(in_experiment),
integration(in_integration),
npixels(experiment.GetPixelsNum()),
xpixels(experiment.GetXPixelsNum()),
indexer(in_indexer),
prediction(CreateBraggPrediction(experiment.IsRotationIndexing())),
mask(in_mask),
mask_resolution(experiment.GetPixelsNum(), false),
mask_high_res(-1),
mask_low_res(-1) {
#ifdef JFJOCH_USE_CUDA
if (get_gpu_count() == 0) {
#endif
preprocessor_buffer = std::make_unique<ImagePreprocessorBuffer>(experiment.GetPixelsNum());
spotFinder = std::make_unique<ImageSpotFinderCPU>(experiment.GetXPixelsNum(), experiment.GetYPixelsNum());
azint = std::make_unique<AzIntEngineCPU>(integration);
preprocessor = std::make_unique<ImagePreprocessorCPU>(in_experiment, in_mask);
if (experiment.ROI().size() >= 1)
roi = std::make_unique<ROIIntegrationCPU>(experiment);
#ifdef JFJOCH_USE_CUDA
} else {
auto stream = std::make_shared<CudaStream>();
preprocessor_buffer = std::make_unique<ImagePreprocessorBufferGPU>(experiment.GetPixelsNum());
preprocessor = std::make_unique<ImagePreprocessorGPU>(in_experiment, in_mask, stream);
spotFinder = std::make_unique<ImageSpotFinderGPU>(experiment.GetXPixelsNum(), experiment.GetYPixelsNum(), stream);
azint = std::make_unique<AzIntEngineGPU>(integration, stream);
if (experiment.ROI().size() >= 1)
roi = std::make_unique<ROIIntegrationGPU>(experiment, stream);
}
#endif
}
void MXAnalysisWithoutFPGA::Analyze(DataMessage &output,
AzimuthalIntegrationProfile &profile,
const SpotFindingSettings &spot_finding_settings) {
if ((output.image.GetWidth() != xpixels)
|| (output.image.GetWidth() * output.image.GetHeight() != npixels))
throw JFJochException(JFJochExceptionCategory::InputParameterInvalid,
"Mismatch in pixel size");
const auto compression_start_time = std::chrono::steady_clock::now();
const uint8_t *image_ptr = output.image.GetUncompressedPtr(decompression_buffer);
const auto compression_end_time = std::chrono::steady_clock::now();
if (output.image.GetCompressionAlgorithm() != CompressionAlgorithm::NO_COMPRESSION)
output.compression_time_s = std::chrono::duration<float>(compression_end_time - compression_start_time).count();
const auto preprocessing_start_time = std::chrono::steady_clock::now();
auto ret = preprocessor->Analyze(*preprocessor_buffer, image_ptr, output.image.GetMode());
const auto preprocessing_end_time = std::chrono::steady_clock::now();
output.preprocessing_time_s = std::chrono::duration<float>(preprocessing_end_time - preprocessing_start_time).count();
const auto azint_start_time = std::chrono::steady_clock::now();
azint->Run(*preprocessor_buffer, profile);
const auto azint_end_time = std::chrono::steady_clock::now();
output.azint_time_s = std::chrono::duration<float>(azint_end_time - azint_start_time).count();
if (roi)
roi->Run(*preprocessor_buffer, output.roi);
if (spot_finding_settings.enable) {
// Update resolution mask
if (mask_high_res != spot_finding_settings.high_resolution_limit
|| mask_low_res != spot_finding_settings.low_resolution_limit)
UpdateMaskResolution(spot_finding_settings);
const auto spot_finding_start_time = std::chrono::steady_clock::now();
const std::vector<DiffractionSpot> spots = spotFinder->Run(*preprocessor_buffer, spot_finding_settings, mask_resolution);
SpotAnalyze(experiment, spot_finding_settings, spots, output);
const auto spot_finding_end_time = std::chrono::steady_clock::now();
output.spot_finding_time_s = std::chrono::duration<float>(spot_finding_end_time - spot_finding_start_time).count();
if (spot_finding_settings.indexing)
indexer.ProcessImage(output, spot_finding_settings,
CompressedImage(preprocessor_buffer->getBuffer(), experiment.GetXPixelsNum(), experiment.GetYPixelsNum()),
*prediction);
}
output.max_viable_pixel_value = ret.max_value;
output.min_viable_pixel_value = ret.min_value;
output.error_pixel_count = ret.error_pixel_count;
output.saturated_pixel_count = ret.saturated_pixel_count;
output.az_int_profile = profile.GetResult();
output.az_int_profile_count = profile.GetPixelCount();
output.az_int_profile_std = profile.GetStd();
output.bkg_estimate = profile.GetBkgEstimate(integration.Settings());
}
void MXAnalysisWithoutFPGA::UpdateMaskResolution(const SpotFindingSettings &settings) {
mask_low_res = settings.low_resolution_limit;
mask_high_res = settings.high_resolution_limit;
auto const &resolution_map = integration.Resolution();
for (int i = 0; i < mask_resolution.size(); i++)
mask_resolution[i] = (resolution_map[i] > mask_low_res) || (resolution_map[i] < mask_high_res);
}